© 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. 22774
    Prev
    Next
    INDEX
    Explanations

    forklift trucks

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

    forklift operation or accidents

    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
    8
    0.64
    5
    0.50
    9
    0.50
     Would
    0.50
    ced
    0.50
    ong
    0.48
    $,
    0.48
    p
    0.47
     Differentiation
    0.46
    c
    0.46
    POSITIVE LOGITS
    น
    0.63
     officiel
    0.59
     giornata
    0.58
     atteint
    0.57
    ’
    0.56
     futebol
    0.54
    ോട്ട
    0.53
    '
    0.53
     acteurs
    0.52
     Dayan
    0.52
    Activations Density 0.001%

    No Known Activations