© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141494
    Prev
    Next
    INDEX
    Explanations

    deemed superseded

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

    affect inference, optimize performance

    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
    т
    0.53
    true
    0.49
    weets
    0.48
    </h2>
    0.45
    ,",
    0.44
    ".
    0.44
    ;
    0.44
    ч
    0.44
    ,
    0.44
    м
    0.43
    POSITIVE LOGITS
    ሉም
    0.52
    🕌
    0.46
     profondes
    0.46
     znajdują
    0.46
    💒
    0.46
    🏙
    0.45
    ほう
    0.45
    dyn
    0.45
    헌
    0.45
     поперед
    0.45
    Activations Density 0.000%

    No Known Activations