© 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. 155730
    Prev
    Next
    INDEX
    Explanations

    punctuation, numbers, and former times

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

    code comments and structure

    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
    Pitts
    0.41
    hydes
    0.37
    脊
    0.36
     biomark
    0.36
    øm
    0.36
    library
    0.36
     libr
    0.36
     Illness
    0.36
    ɬ
    0.35
     Library
    0.35
    POSITIVE LOGITS
     autrefois
    0.59
     formerly
    0.45
     Formerly
    0.45
     سابقا
    0.45
    Formerly
    0.43
     WOULD
    0.39
     neither
    0.39
     ไม่
    0.38
     <!--<
    0.38
    を用
    0.38
    Activations Density 0.001%

    No Known Activations