© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177920
    Prev
    Next
    INDEX
    Explanations

    history, century, child, welfare, anonymous, army

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

    ancient roots, local experiences, financial statements, parse data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     डेवलपमेंट
    0.46
    决心
    0.46
    湁
    0.46
    கால
    0.46
    颜值
    0.46
     याबाबत
    0.45
    鉭
    0.45
    颌
    0.45
     Entscheidung
    0.45
    Preis
    0.45
    POSITIVE LOGITS
    :
    0.50
    cycle
    0.43
     ব্যব
    0.42
     purchases
    0.41
     condensers
    0.41
    стіше
    0.41
     март
    0.41
     purchasers
    0.41
     servers
    0.40
    :<
    0.40
    Activations Density 0.002%

    No Known Activations