© 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. 94934
    Prev
    Next
    INDEX
    Explanations

    Egypt, first air

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

    reviewers, goals, internal, personal

    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
    enter
    0.46
    warp
    0.45
    Corner
    0.45
    row
    0.45
    rota
    0.43
    N
    0.43
    Fashion
    0.43
    }-
    0.42
    onDestroy
    0.42
    वारा
    0.41
    POSITIVE LOGITS
     கொண்ட
    0.55
     declines
    0.55
     χα
    0.52
     exemptions
    0.51
     Συν
    0.51
     الات
    0.50
     ۵
    0.50
     ампли
    0.50
     DISPLAYS
    0.50
    ازت
    0.50
    Activations Density 0.001%

    No Known Activations