© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11557
    Prev
    Next
    INDEX
    Explanations

    POS tags and abbreviations

    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
    groups
    -0.94
     as
    -0.93
     lateinit
    -0.91
     चुन
    -0.90
     choose
    -0.90
     options
    -0.90
     chosen
    -0.89
    setViewName
    -0.89
     to
    -0.88
    Salut
    -0.87
    POSITIVE LOGITS
    ையும்
    1.03
    無論
    1.02
     BOTH
    1.01
    ITHER
    0.97
     เปิด
    0.96
    Both
    0.96
    どっち
    0.95
    取决
    0.94
    脔
    0.93
     현재
    0.93
    Activations Density 0.003%

    No Known Activations