© 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. 245501
    Prev
    Next
    INDEX
    Explanations

    tax changes

    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
     Ook
    0.48
    7
    0.48
     নিয়ে
    0.47
    ."""
    0.47
    4
    0.46
     Operation
    0.45
     Zoo
    0.45
    us
    0.45
    ।’’
    0.45
    .’
    0.44
    POSITIVE LOGITS
    ગર
    0.47
    absorbed
    0.46
     knobs
    0.46
    城乡
    0.45
     fixer
    0.45
    陥
    0.44
     bushels
    0.44
     spal
    0.43
    IFIED
    0.43
    bevel
    0.43
    Activations Density 0.000%

    No Known Activations