© 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. 75257
    Prev
    Next
    INDEX
    Explanations

    flee in terror

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

    integrating

    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
     the
    0.64
    T
    0.56
    the
    0.56
     of
    0.52
     both
    0.50
    Poland
    0.50
    A
    0.50
    I
    0.49
    J
    0.49
    R
    0.48
    POSITIVE LOGITS
     อืม
    0.57
     পোশাক
    0.54
    个小时
    0.50
    嬷
    0.50
     атаку
    0.49
     तकरीबन
    0.48
     решил
    0.48
    nungen
    0.48
     এক
    0.47
     ड्रग
    0.47
    Activations Density 0.001%

    No Known Activations