© 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. 59614
    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
    2
    -3.02
    1
    -2.97
    <i>
    -2.75
    <b>
    -2.64
    3
    -2.63
    4
    -2.61
    7
    -2.38
    –
    -2.33
    B
    -2.31
    s
    -2.28
    POSITIVE LOGITS
     it
    2.41
    薦
    1.93
    %">
    1.89
    月号
    1.88
    偌
    1.83
     веке
    1.82
    _),
    1.78
    ApJ
    1.77
    𝑥
    1.77
     hacían
    1.76
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.