© 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. 22-GEMMASCOPE-RES-131K
    7. 32860
    Prev
    Next
    INDEX
    Explanations

    code initialization

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     \
    -1.32
     \"
    -1.27
     páss
    -1.19
     ''
    -1.13
     ""
    -1.10
     Japão
    -1.07
     settembre
    -1.07
    に使用
    -1.05
    ;%%
    -1.05
     "
    -1.03
    POSITIVE LOGITS
    <bos>
    1.64
    Intérieur
    1.23
     ameste
    1.21
    がありますが
    1.17
    אני
    1.15
     Fällen
    1.15
    というわけで
    1.15
     ところ
    1.13
    Ofer
    1.13
     REI
    1.09
    Activations Density 0.000%

    No Known Activations