© 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. 80625
    Prev
    Next
    INDEX
    Explanations

    oily feel, hands above

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

    personality and temperatures

    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
    i
    0.54
    ak
    0.52
    ToJava
    0.51
     [];
    0.48
     mendapat
    0.48
    ai
    0.48
     treffen
    0.47
    ist
    0.47
     has
    0.46
     '';
    0.46
    POSITIVE LOGITS
    지는
    0.54
    افل
    0.50
    ᑕ
    0.48
    tida
    0.47
    姩
    0.47
    мл
    0.46
    لق
    0.46
    ᔕ
    0.46
    尸
    0.46
    تى
    0.46
    Activations Density 0.000%

    No Known Activations