© 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. 172259
    Prev
    Next
    INDEX
    Explanations

    Canadian locations and parks

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

    personality, war decision

    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
    m
    0.55
    grep
    0.49
    cabinet
    0.48
    हिर
    0.48
    Holy
    0.48
    s
    0.47
    2
    0.47
    in
    0.47
    holy
    0.46
    p
    0.46
    POSITIVE LOGITS
     Yamazaki
    0.59
     टेंपरेचर
    0.55
     вмі
    0.51
     ପ୍ର
    0.51
     माइ
    0.50
     އ
    0.49
     让
    0.49
     以及
    0.49
     }{}_{\
    0.49
     aí
    0.48
    Activations Density 0.000%

    No Known Activations