© 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. 44282
    Prev
    Next
    INDEX
    Explanations

    from __future__ import

    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
    .
    -2.17
    1
    -1.80
    </em>
    -1.71
     "
    -1.71
      
    -1.60
    ,
    -1.60
     Other
    -1.59
    <em>
    -1.52
    </h2>
    -1.46
     there
    -1.45
    POSITIVE LOGITS
    MAXN
    1.96
    可以
    1.77
    ϐ
    1.72
    szt
    1.59
    鼱
    1.59
    %;
    1.57
    üglich
    1.55
    maxn
    1.52
    nige
    1.52
    需要
    1.50
    Activations Density 0.004%

    No Known Activations