© 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. 120845
    Prev
    Next
    INDEX
    Explanations

    eating arms

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

    breakdown of what X means

    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
    $.
    0.50
    sons
    0.48
    weather
    0.46
    apy
    0.46
    ----
    0.46
    [,
    0.46
    k
    0.46
    Statement
    0.45
    statement
    0.45
    --
    0.45
    POSITIVE LOGITS
     dédi
    0.49
    瑠
    0.49
     Rouge
    0.46
    पीरियंस
    0.46
     daripada
    0.45
    நபியே
    0.45
     dédiée
    0.44
     devast
    0.44
     sempurna
    0.43
     fistule
    0.43
    Activations Density 0.001%

    No Known Activations