© 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. 73432
    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
    atser
    -1.34
     to
    -1.27
     triliun
    -1.19
    x
    -1.16
     började
    -1.15
     卧室
    -1.14
     dogged
    -1.12
    zzlement
    -1.12
    crania
    -1.12
     has
    -1.12
    POSITIVE LOGITS
    <bos>
    1.91
     herre
    1.50
    (“
    1.47
    肏
    1.38
     mily
    1.36
     fuis
    1.26
     itſelf
    1.26
     fers
    1.24
    -“
    1.23
     mitra
    1.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.