© 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. 122886
    Prev
    Next
    INDEX
    Explanations

    still allows or enables

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

    understanding complex concepts or actions

    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
     जात
    0.49
    वानगी
    0.48
    ،
    0.47
    🪜
    0.46
    óri
    0.46
     माला
    0.45
     ವಿಧಾನಸ
    0.45
    مت
    0.44
    गण
    0.44
     fáb
    0.44
    POSITIVE LOGITS
    ровка
    0.49
     Pentru
    0.47
     Cómo
    0.46
    جمالي
    0.46
    Pentru
    0.45
    getFullName
    0.45
    getFull
    0.44
     =-\
    0.44
     accentuated
    0.44
    unoscut
    0.43
    Activations Density 0.000%

    No Known Activations