© 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. 163684
    Prev
    Next
    INDEX
    Explanations

    offers, services, or outcomes

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

    ad headlines

    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
    ગવાન
    0.52
    াদনের
    0.48
    哫
    0.48
    ለያዩ
    0.46
    ляць
    0.46
    throws
    0.44
    ွက်
    0.43
    ახებ
    0.43
    ά
    0.43
     Kurds
    0.43
    POSITIVE LOGITS
    0.52
     العمل
    0.45
     usefulness
    0.45
     protest
    0.45
     paž
    0.44
     comportamenti
    0.44
     antics
    0.44
     catatan
    0.44
     &(
    0.43
     tricks
    0.43
    Activations Density 0.000%

    No Known Activations