© 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. 174473
    Prev
    Next
    INDEX
    Explanations

    events and consequences

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

    legal and storytelling

    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
    I
    0.62
    Untuk
    0.56
    Pentru
    0.55
    Tel
    0.53
    C
    0.52
    PMS
    0.51
    S
    0.50
    Questa
    0.50
    X
    0.50
    Xi
    0.50
    POSITIVE LOGITS
     Legislative
    0.46
     sympathy
    0.45
     رائے
    0.44
     Casualty
    0.43
     Voc
    0.43
     Happened
    0.43
     tradeoff
    0.43
     Scientific
    0.42
     Crimea
    0.42
     Maharashtra
    0.42
    Activations Density 0.000%

    No Known Activations