© 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. 62067
    Prev
    Next
    INDEX
    Explanations

    to logged-in members

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

    useful for connecting

    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
     ключе
    0.42
     gradi
    0.41
     apiClient
    0.41
    лих
    0.41
    रियल
    0.41
     যাব
    0.40
     ছাড়া
    0.40
    $-$
    0.40
     rocky
    0.40
     clés
    0.39
    POSITIVE LOGITS
    dichlor
    0.47
    ্‌
    0.47
     Ví
    0.47
     Eğer
    0.46
    muk
    0.45
    ア
    0.45
    níka
    0.45
    ंना
    0.45
    者に
    0.45
    とっても
    0.45
    Activations Density 0.000%

    No Known Activations