© 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. 136916
    Prev
    Next
    INDEX
    Explanations

    normal footwear

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

    your perspective or how you navigate

    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
     (
    0.57
     jail
    0.50
     st
    0.49
     dialysis
    0.49
     key
    0.48
     wine
    0.48
     wire
    0.47
     laser
    0.46
     biome
    0.46
     voltage
    0.46
    POSITIVE LOGITS
    reflectionCamera
    0.54
    ...');
    0.52
    tdev
    0.51
     мои
    0.49
    職業
    0.49
    adonis
    0.49
    риев
    0.49
     Олимпий
    0.49
    adayo
    0.49
    arys
    0.48
    Activations Density 0.000%

    No Known Activations