© 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. 127919
    Prev
    Next
    INDEX
    Explanations

    how to find or start

    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
    miyor
    -1.25
     dör
    -1.23
     витами
    -1.23
    علام
    -1.22
     Saturday
    -1.22
    nytt
    -1.20
    ::_('
    -1.20
     women
    -1.20
    覺得
    -1.19
     história
    -1.19
    POSITIVE LOGITS
     project
    1.37
     VIH
    1.30
    FONTE
    1.20
    龕
    1.19
    begingroup
    1.19
    うま
    1.17
    ूह
    1.16
     resources
    1.16
     projects
    1.14
     develop
    1.13
    Activations Density 0.238%

    No Known Activations