© 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. 7292
    Prev
    Next
    INDEX
    Explanations

    treadmill and store

    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
    </td>
    -2.95
    虽说
    -2.28
    "]();
    -2.27
    </h5>
    -2.02
    荭
    -1.82
     vorigen
    -1.75
    ↵↵↵↵
    -1.73
     Veränder
    -1.73
    蟜
    -1.72
    </b>
    -1.71
    POSITIVE LOGITS
    y
    2.22
    '
    2.02
     szczeg
    1.98
     lots
    1.89
    𝐿
    1.88
    it
    1.81
     cht
    1.79
    bison
    1.74
     dadas
    1.73
    喟
    1.73
    Activations Density 0.007%

    No Known Activations