© 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. 15370
    Prev
    Next
    INDEX
    Explanations

    form method post or get

    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
    луйста
    -1.89
    Filmography
    -1.78
    }*/
    -1.76
    tichetta
    -1.73
    銠
    -1.73
     frå
    -1.67
    ünster
    -1.66
    ⡦
    -1.66
    "}";
    -1.66
     firft
    -1.66
    POSITIVE LOGITS
    .
    2.89
    re
    1.99
     method
    1.96
     Whether
    1.80
     This
    1.80
     Many
    1.80
     calculate
    1.78
     While
    1.77
     Therefore
    1.76
    设计的
    1.74
    Activations Density 0.068%

    No Known Activations