© 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. 101923
    Prev
    Next
    INDEX
    Explanations

    indicates what's next or points

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

    short legs

    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
    紘
    0.50
     Silvio
    0.48
    は
    0.44
    を用
    0.43
    厛
    0.43
    っては
    0.43
    ׃
    0.43
    Та
    0.43
    であった
    0.42
     DefaultTargets
    0.42
    POSITIVE LOGITS
    cana
    0.52
    kjav
    0.50
    can
    0.49
    render
    0.49
    caf
    0.49
    kj
    0.49
    cante
    0.48
     vocational
    0.48
    ter
    0.48
    ak
    0.48
    Activations Density 0.000%

    No Known Activations