© 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. 26538
    Prev
    Next
    INDEX
    Explanations

    custom report

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

    numbers and calculations

    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
    чень
    0.37
    Whether
    0.37
     unsigned
    0.37
     notifications
    0.37
     atmosfera
    0.37
    시
    0.37
    ף
    0.35
     resume
    0.35
    ANIEL
    0.35
    чина
    0.34
    POSITIVE LOGITS
     LikeLike
    0.42
     Stirling
    0.40
     Igu
    0.39
    sadquotes
    0.39
    aing
    0.37
    اعر
    0.37
     สะ
    0.37
     Shad
    0.37
    Ⅶ
    0.36
    úč
    0.36
    Activations Density 0.000%

    No Known Activations