© 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. 1227
    Prev
    Next
    INDEX
    Explanations

    code, scripts, and instructions

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

    code blocks and keywords

    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
     nadal
    0.30
     provin
    0.29
     vestir
    0.29
     história
    0.29
    يني
    0.29
     žel
    0.29
    𒊩
    0.29
     similit
    0.28
     compreender
    0.28
     വിശ
    0.28
    POSITIVE LOGITS
    ...*/
    0.32
    public
    0.30
     ...
    0.29
    ...",
    0.28
    ...");
    0.28
     来自
    0.28
    type
    0.28
     =>
    0.28
     Foo
    0.28
    有个
    0.27
    Activations Density 0.037%

    No Known Activations