© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75074
    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
    durante
    -1.95
    肜
    -1.82
     série
    -1.72
    上げた
    -1.71
     stör
    -1.66
    ן
    -1.66
    蕻
    -1.62
    ﻝ
    -1.57
    ㋛
    -1.56
    ónde
    -1.55
    POSITIVE LOGITS
    '
    1.96
    氿
    1.66
    ),
    1.57
    >
    1.57
     آنان
    1.44
    %
    1.40
    amp
    1.36
     $*$
    1.35
    ...)
    1.34
     CAPIT
    1.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.