© 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. 84000
    Prev
    Next
    INDEX
    Explanations

    Service

    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
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -3.19
     There
    -2.92
     When
    -2.80
     Before
    -2.77
     During
    -2.75
     some
    -2.69
     two
    -2.63
     Since
    -2.55
     three
    -2.52
     Despite
    -2.48
    POSITIVE LOGITS
    鹩
    2.56
     Dinas
    2.42
     😊
    2.31
    formatics
    2.25
    !!!!!!!
    2.23
    asters
    2.20
    particularly
    2.14
     incredi
    2.14
    鹇
    2.13
     😁
    2.11
    Activations Density 0.058%

    No Known Activations