© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112977
    Prev
    Next
    INDEX
    Explanations

    copyright notices and company names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    increases
    -1.70
     reveló
    -1.65
    为啥
    -1.63
    possibly
    -1.60
    }));
    -1.59
    ¸
    -1.55
     requiere
    -1.52
    often
    -1.52
     anunció
    -1.52
    throughout
    -1.51
    POSITIVE LOGITS
     for
    1.95
     which
    1.67
     also
    1.59
     what
    1.55
    這
    1.52
     having
    1.52
     such
    1.51
     doing
    1.51
    เรา
    1.47
    他
    1.47
    Activations Density 0.072%

    No Known Activations