© 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. 212253
    Prev
    Next
    INDEX
    Explanations

    customer accounts and relations

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

    Increased Productivity

    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
    頗
    0.50
     gradioApp
    0.48
    fieldName
    0.47
    <bbox>
    0.47
    pageNum
    0.46
    )}^
    0.46
    toprule
    0.46
    素晴
    0.46
    舉辦
    0.46
    왼
    0.45
    POSITIVE LOGITS
     calling
    0.51
     Ин
    0.50
     hell
    0.50
     monarchy
    0.50
     there
    0.49
     you
    0.49
     tactical
    0.48
     gaming
    0.48
     captivity
    0.48
     ability
    0.47
    Activations Density 0.000%

    No Known Activations