© 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. 25668
    Prev
    Next
    INDEX
    Explanations

    documentation comments @param @returns

    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
     tani
    -1.13
     matic
    -1.03
     vola
    -1.02
     菇
    -1.02
     raha
    -1.00
     aspek
    -1.00
     klip
    -0.98
     kaka
    -0.96
     fabri
    -0.96
     hama
    -0.96
    POSITIVE LOGITS
     Obviously
    1.15
     h
    1.15
     after
    1.02
     or
    1.01
     //
    0.95
    Obviously
    0.94
     p
    0.93
    h
    0.91
     if
    0.91
    🧾
    0.91
    Activations Density 0.002%

    No Known Activations