© 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. 3376
    Prev
    Next
    INDEX
    Explanations

    GM greeting

    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
    Not in Any Lists

    No Comments

    Negative Logits
     efectivo
    -0.98
     horizontal
    -0.78
     treffen
    -0.77
    active
    -0.77
     criminal
    -0.75
     serve
    -0.75
     географи
    -0.73
    tomic
    -0.73
    serve
    -0.73
     tapa
    -0.72
    POSITIVE LOGITS
     GM
    1.02
     Gm
    0.97
     gm
    0.91
    цева
    0.77
    gm
    0.75
    adilan
    0.74
     Hela
    0.73
     Held
    0.72
    GM
    0.71
     Angele
    0.70
    Activations Density 0.047%

    No Known Activations