© 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. 158656
    Prev
    Next
    INDEX
    Explanations

    brute force

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

    parenthetical explanations and remarks

    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
     mutate
    0.57
    쯔
    0.44
    тар
    0.43
    реди
    0.43
     mutated
    0.43
    mutate
    0.43
    致命
    0.43
    fato
    0.43
    МИ
    0.43
    Stopped
    0.42
    POSITIVE LOGITS
     jov
    0.52
    显著
    0.48
     realiz
    0.47
     春
    0.45
     betreff
    0.45
     न
    0.44
     alcune
    0.44
    ibusdam
    0.44
     woll
    0.44
     ছাড়া
    0.44
    Activations Density 0.000%

    No Known Activations