© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15271
    Prev
    Next
    INDEX
    Explanations

    major draw for viewers

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects expressions of pride or self-praise in staff bios (e.g. “takes pride in…”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    professional or business language emphasizing quality, service, and commitment.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mission- and marketing-style statements that promote an organization’s services by emphasizing experience, quality, professionalism, pride, guarantees, and client-focused care.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vermutlich
    0.90
    Interestingly
    0.83
     trochu
    0.81
     Interestingly
    0.77
     içeren
    0.74
     podría
    0.72
     deaktiv
    0.72
     poderia
    0.72
     perde
    0.72
     lidt
    0.72
    POSITIVE LOGITS
    常に
    1.26
     our
    1.23
     customer
    1.20
    客户
    1.20
     strives
    1.20
     customers
    1.20
     Kunden
    1.18
    客戶
    1.16
     Customers
    1.15
    我们的
    1.14
    Activations Density 1.374%

    No Known Activations