© 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. 113885
    Prev
    Next
    INDEX
    Explanations

    all the way

    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
     ingat
    -2.19
     обладает
    -1.92
     evidente
    -1.77
     sposo
    -1.75
     prenant
    -1.73
     laku
    -1.65
    瞜
    -1.64
    嗵
    -1.62
    辚
    -1.61
     relâche
    -1.60
    POSITIVE LOGITS
     Even
    1.98
     Both
    1.81
     Когда
    1.77
     There
    1.77
    quarelle
    1.76
     When
    1.74
     allgemeinen
    1.73
     Isn
    1.72
     Although
    1.71
     According
    1.71
    Activations Density 0.009%

    No Known Activations