© 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. 222916
    Prev
    Next
    INDEX
    Explanations

    various occupations and descriptions

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

    lists, commands, or predictions

    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
     fabs
    0.46
    쩝
    0.45
     cm
    0.44
     kinetics
    0.43
    ]");
    0.43
     Industry
    0.42
     imputation
    0.42
    Ü
    0.42
     hö
    0.42
    介
    0.42
    POSITIVE LOGITS
    Wisconsin
    0.53
     jogador
    0.51
    anego
    0.50
    atual
    0.50
    alie
    0.50
    acar
    0.50
    jogador
    0.49
    entro
    0.48
    aguars
    0.47
     giocatori
    0.46
    Activations Density 0.001%

    No Known Activations