© 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. 68092
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ثمان
    -2.77
     With
    -2.69
     thwart
    -2.64
     steadfast
    -2.45
    uckoo
    -2.44
    the
    -2.39
    тися
    -2.36
    冏
    -2.33
    僭
    -2.33
     Since
    -2.30
    POSITIVE LOGITS
    rd
    3.61
    3
    3.47
    i
    3.27
    et
    2.67
    ，”
    2.52
    end
    2.48
    gucig
    2.48
     lakini
    2.44
    r
    2.44
    甞
    2.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.