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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36549
    Prev
    Next
    INDEX
    Explanations

    Neural tube defects, Allergic

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

    struct field definitions in Go programming language.

    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
     $\
    -1.35
     $
    -1.34
     will
    -1.30
     would
    -1.25
    cím
    -1.21
     pourrez
    -1.19
    sobí
    -1.14
     is
    -1.13
     could
    -1.13
    рите
    -1.12
    POSITIVE LOGITS
     hermosas
    1.40
     mittler
    1.29
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.26
     てき
    1.25
    to
    1.25
     manquer
    1.24
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.23
     می‌کن
    1.23
    </h1>
    1.23
    дәбият
    1.21
    Activations Density 0.006%

    No Known Activations