© 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. 34-GEMMASCOPE-RES-131K
    7. 56692
    Prev
    Next
    INDEX
    Explanations

    card body content

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     header
    -1.29
    header
    -1.18
     HEADER
    -1.15
    HEADER
    -1.14
     Header
    -1.11
    Header
    -1.04
     headers
    -1.00
     headed
    -0.98
     headline
    -0.97
    getHeader
    -0.91
    POSITIVE LOGITS
     body
    1.66
    Body
    1.27
    CardBody
    1.23
     Body
    1.18
    body
    1.16
     cuerpo
    1.16
    CardContent
    1.13
     BODY
    1.12
     bodies
    1.03
    getBody
    1.03
    Activations Density 0.010%

    No Known Activations