© 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. 1251
    Prev
    Next
    INDEX
    Explanations

    purpose limitation or inherent sexual

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    initions
    0.75
    ákat
    0.73
     संथाल
    0.72
     října
    0.70
    اتها
    0.70
    َّة
    0.70
    쩡
    0.70
    िंग
    0.69
    ić
    0.69
    ai
    0.68
    POSITIVE LOGITS
    Przyp
    0.77
     Quadrup
    0.71
    ക്കായി
    0.68
    基督教
    0.68
    请
    0.68
    ('
    0.68
    จะ
    0.67
     enteros
    0.67
    尽
    0.67
    要
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.