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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15169
    Prev
    Next
    INDEX
    Explanations

    protected characteristics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    acotta
    0.65
    নাট
    0.65
     カメラ
    0.61
     を
    0.60
    ostics
    0.60
     ধর্
    0.60
     之
    0.59
     Races
    0.59
    ᅳ
    0.59
     bottomRight
    0.59
    POSITIVE LOGITS
     pregnancy
    1.07
     protected
    1.04
     embarazo
    0.98
     marital
    0.94
    pregnancy
    0.94
     veteran
    0.89
     Protected
    0.87
     Pregnancy
    0.86
     handicap
    0.84
     pregnant
    0.84
    Activations Density 0.006%

    No Known Activations