© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15560
    Prev
    Next
    INDEX
    Explanations

    Montgomery, stdint, Cordova

    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
    Negative Logits
    是
    -2.80
     spannende
    -2.77
    哢
    -2.69
     comprennent
    -2.61
    然后
    -2.47
     THEY
    -2.47
     如果
    -2.44
     incluem
    -2.38
     Their
    -2.36
    CHREIB
    -2.34
    POSITIVE LOGITS
    the
    3.77
    e
    3.48
    k
    3.41
    a
    3.25
    ."
    3.14
    d
    3.11
    B
    2.89
    this
    2.81
    as
    2.81
    U
    2.80
    Activations Density 0.005%

    No Known Activations