© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84182
    Prev
    Next
    INDEX
    Explanations

    method of doing

    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
    If
    -1.94
    輒
    -1.91
     you
    -1.73
     thailand
    -1.72
    When
    -1.67
    For
    -1.62
     {
    -1.60
     })
    -1.55
     становится
    -1.53
    y
    -1.52
    POSITIVE LOGITS
     a
    1.93
     aranha
    1.87
     borboleta
    1.85
     Bedürf
    1.80
     sereia
    1.79
     other
    1.73
     egyéb
    1.73
     erfordert
    1.73
     Durchschnitt
    1.73
    ان
    1.66
    Activations Density 0.003%

    No Known Activations