© 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. 57981
    Prev
    Next
    INDEX
    Explanations

    script tags

    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
     from
    -1.69
     different
    -1.46
     other
    -1.45
     only
    -1.45
     until
    -1.42
     one
    -1.41
     on
    -1.41
     if
    -1.38
     even
    -1.38
     each
    -1.38
    POSITIVE LOGITS
     recente
    1.45
    "{\
    1.41
    Bibliografie
    1.41
    quartered
    1.40
     SAMSUNG
    1.38
    </strong>
    1.38
     både
    1.37
     `,
    1.36
    &&&&
    1.35
     Posteriormente
    1.35
    Activations Density 0.047%

    No Known Activations