© 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. 50132
    Prev
    Next
    INDEX
    Explanations

    streetscape, remote, contracts

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

    opposition, Symbol, protocol, Lower, cats

    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
    select
    0.46
    columnIndex
    0.46
    m
    0.45
    is
    0.44
    formula
    0.44
    te
    0.43
    trailing
    0.42
    in
    0.42
    became
    0.42
    recipes
    0.42
    POSITIVE LOGITS
     carcinogenesis
    0.54
     êtres
    0.50
     cityscape
    0.46
    祸
    0.46
     skyscrapers
    0.45
     począ
    0.45
     horrors
    0.45
     heartbreaking
    0.45
     eksempel
    0.45
     humaine
    0.44
    Activations Density 0.001%

    No Known Activations