© 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. 225138
    Prev
    Next
    INDEX
    Explanations

    T. brucei, Griffin, robber

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

    assurance awareness guarantee

    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
     profitably
    0.58
    ्रु
    0.50
    ذیر
    0.47
     immunized
    0.47
    ड़का
    0.46
    队
    0.45
     trước
    0.44
     ナイス
    0.44
     stér
    0.44
     күзгү
    0.44
    POSITIVE LOGITS
    ua
    0.50
    uar
    0.49
    č
    0.46
    ub
    0.45
     Advice
    0.44
    ._
    0.44
    oble
    0.44
    urance
    0.43
    jum
    0.43
    aku
    0.42
    Activations Density 0.000%

    No Known Activations