© 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. 94236
    Prev
    Next
    INDEX
    Explanations

    graph access methods

    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
     estaría
    -0.98
     by
    -0.95
     now
    -0.85
     selon
    -0.85
     conoció
    -0.84
    ner
    -0.84
     It
    -0.83
    襖
    -0.81
    fant
    -0.81
     Santa
    -0.79
    POSITIVE LOGITS
    —
    0.99
    ━
    0.98
    this
    0.95
    יש
    0.94
    €”
    0.93
    WHERE
    0.93
     –
    0.93
    Имя
    0.93
    -//
    0.93
    大人気
    0.93
    Activations Density 0.000%

    No Known Activations