© 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. 128596
    Prev
    Next
    INDEX
    Explanations

    e.g. or example

    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
    +};
    -1.09
    就开始
    -1.03
     categoria
    -0.96
    setminus
    -0.94
    に住
    -0.94
     CATEGORIES
    -0.94
     category
    -0.94
    msgTypes
    -0.93
     BigNumberish
    -0.91
     we
    -0.90
    POSITIVE LOGITS
    isNotBlank
    1.06
    金币
    1.05
     antworte
    1.04
    znych
    1.03
     daarna
    0.98
    Referensi
    0.95
     např
    0.95
    惆
    0.94
     hjär
    0.94
    vestidos
    0.94
    Activations Density 0.033%

    No Known Activations