© 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. 3428
    Prev
    Next
    INDEX
    Explanations

    functional and structural connectivity

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

    The neuron detects subjective or self-referential language—especially first-person possessives (“my”) and evaluative or promotional adjectives (“trendy”).

    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
    𝒂
    0.91
    𝒐
    0.82
    ୌ
    0.80
    وري
    0.79
    ন
    0.79
     pouces
    0.78
     યો
    0.78
    ן
    0.77
    ות
    0.76
    ورية
    0.76
    POSITIVE LOGITS
    ጣጠ
    0.75
     perturb
    0.73
     ALS
    0.73
    ↵
    0.72
    fff
    0.72
    ---->
    0.71
    sic
    0.70
     Cint
    0.69
     meromorphic
    0.69
     particular
    0.68
    Activations Density 0.000%

    No Known Activations