© 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. 12349
    Prev
    Next
    INDEX
    Explanations

    via β-adrenoceptors

    np_acts-logits-general · gemini-2.5-flash-lite

    code and technical notations such as file paths, error messages, and programming syntax.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    MultipartFile
    -0.88
    UPLOAD
    -0.88
    kamp
    -0.82
    wohnung
    -0.79
    源
    -0.79
     STRUCTURE
    -0.76
    FormState
    -0.75
    Skeleton
    -0.75
    Strategy
    -0.74
    Loose
    -0.74
    POSITIVE LOGITS
    antung
    0.83
     sintética
    0.81
     desses
    0.80
    ^*)
    0.77
    が可能
    0.72
     asegurarse
    0.71
     manne
    0.71
    wość
    0.70
    δά
    0.70
     успех
    0.70
    Activations Density 0.160%

    No Known Activations