© 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. 22-GEMMASCOPE-RES-131K
    7. 26725
    Prev
    Next
    INDEX
    Explanations

    months, units, oxaliplatin

    np_acts-logits-general · gemini-2.5-flash-lite

    numeric values and measurements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     first
    -1.16
     specific
    -1.07
     excessively
    -1.01
     only
    -0.96
     after
    -0.96
     more
    -0.91
     Since
    -0.90
     considerably
    -0.90
     one
    -0.89
     good
    -0.88
    POSITIVE LOGITS
    ̴
    1.04
    TimeSpan
    1.02
    ˃
    1.01
     фу
    1.00
    iving
    1.00
    ʹ
    0.98
     wśród
    0.97
    stered
    0.96
     AMAZING
    0.95
     Bá
    0.89
    Activations Density 0.042%

    No Known Activations