© 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. 59431
    Prev
    Next
    INDEX
    Explanations

    information dissemination

    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
     dichter
    -1.78
     trois
    -1.71
     aparatos
    -1.64
     queridos
    -1.62
    และ
    -1.59
     considérons
    -1.59
    dö
    -1.57
     BEAUTIFUL
    -1.56
     verborgen
    -1.56
     deux
    -1.55
    POSITIVE LOGITS
     about
    2.80
     who
    1.92
    not
    1.88
    er
    1.78
     with
    1.70
    !
    1.70
     Not
    1.70
     that
    1.63
     for
    1.62
    delijk
    1.61
    Activations Density 0.012%

    No Known Activations