© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1486
    Prev
    Next
    INDEX
    Explanations

    reinforcement learning

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

    The neuron strongly activates on passages giving concrete, detail-rich explanations or instructions—i.e. technical or “how-to” style prose describing real-world processes or specifications.

    oai_token-act-pair · o4-miniTriggered 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
     système
    0.78
    Founded
    0.78
     méthod
    0.74
     saluto
    0.74
    Z
    0.73
    attend
    0.72
     கூறு
    0.70
    prehensive
    0.70
     pien
    0.69
    قال
    0.68
    POSITIVE LOGITS
     itineraries
    0.94
     plantings
    0.91
     comorbidities
    0.91
     lysates
    0.86
    ຳ
    0.82
     automorphisms
    0.82
     trusses
    0.82
     windings
    0.81
     resonances
    0.79
     intermittently
    0.79
    Activations Density 0.009%

    No Known Activations