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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12383
    Prev
    Next
    INDEX
    Explanations

    surface morphology and structure

    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
    而
    -0.92
     BOTH
    -0.83
    🇹
    -0.82
    endió
    -0.79
    raisers
    -0.79
    篋
    -0.79
     peur
    -0.78
    payers
    -0.77
    所以
    -0.77
    ไม่มี
    -0.77
    POSITIVE LOGITS
    :
    0.98
     rather
    0.91
     of
    0.82
     con
    0.79
    only
    0.78
    上官
    0.77
     と
    0.76
     approximately
    0.76
    你说
    0.75
     discussion
    0.74
    Activations Density 0.118%

    No Known Activations