© 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. 65720
    Prev
    Next
    INDEX
    Explanations

    specific context indicators

    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_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
     in
    -2.50
     on
    -2.30
     epitom
    -2.27
     for
    -2.19
     as
    -2.17
     because
    -2.06
     by
    -2.00
     an
    -1.98
     at
    -1.98
     one
    -1.96
    POSITIVE LOGITS
    both
    1.84
     Dinas
    1.79
     .......
    1.77
     !!!!
    1.73
    approximately
    1.67
     鸡蛋
    1.60
     AMAZING
    1.60
     brilh
    1.59
    six
    1.58
     CURRENT
    1.58
    Activations Density 0.504%

    No Known Activations