© 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. 16390
    Prev
    Next
    INDEX
    Explanations

    comparisons of groups or entities

    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
     from
    -1.15
     such
    -1.14
     its
    -0.93
     with
    -0.89
    者に
    -0.87
    ネットで
    -0.86
     and
    -0.85
    amesh
    -0.85
     OPINION
    -0.84
    になりたい
    -0.81
    POSITIVE LOGITS
    jsonPath
    1.08
     debido
    1.02
    がありますが
    0.96
     порядок
    0.94
    留在
    0.94
     общего
    0.93
     나는
    0.93
     poiché
    0.92
    readObject
    0.92
     في
    0.90
    Activations Density 0.050%

    No Known Activations