© 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. 145567
    Prev
    Next
    INDEX
    Explanations

    locations, obligations, or growth

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

    keywords and lists

    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
    ško
    0.49
    ó
    0.48
    ża
    0.47
     jako
    0.46
     zast
    0.45
     peasant
    0.45
    ż
    0.45
    कात
    0.45
    ist
    0.44
    க்கை
    0.44
    POSITIVE LOGITS
     подготовки
    0.47
    |}{
    0.45
     crossovers
    0.45
     подру
    0.45
     انتظار
    0.45
     разрешения
    0.45
     صہی
    0.44
    ಯ್
    0.44
     Trains
    0.44
     تشخیص
    0.43
    Activations Density 0.000%

    No Known Activations