© 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. 28265
    Prev
    Next
    INDEX
    Explanations

    specific locations and details

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

    actions taken by

    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
    st
    0.57
    th
    0.55
    8
    0.54
    abs
    0.53
     v
    0.52
    abd
    0.52
    v
    0.52
    NO
    0.52
    es
    0.50
    el
    0.50
    POSITIVE LOGITS
     défin
    0.51
     chimie
    0.51
     স্কোর
    0.50
     реаги
    0.49
    geoType
    0.49
    ѝ
    0.48
     effectué
    0.46
    HttpMethod
    0.46
     trattano
    0.46
    প্রকার
    0.46
    Activations Density 0.000%

    No Known Activations