© 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. 32889
    Prev
    Next
    INDEX
    Explanations

    file paths and licensing information

    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
    Not in Any Lists

    No Comments

    Negative Logits
     or
    -1.34
     had
    -1.24
     while
    -1.23
     could
    -1.13
     with
    -1.09
     this
    -1.08
     would
    -1.02
     from
    -0.96
     метра
    -0.95
    ":"",
    -0.93
    POSITIVE LOGITS
    bkz
    1.45
     ecran
    1.23
    README
    1.22
    捽
    1.20
     nettoyer
    1.15
     uſe
    1.11
     urbano
    1.10
     Moscú
    1.09
     Diſ
    1.09
     \%$.
    1.09
    Activations Density 0.031%

    No Known Activations