© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90840
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

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

    ASCII art or graphical elements in code and text files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects ASCII-art line-drawing characters and patterns (e.g. slashes, backslashes, pipes, underscores) used to form text-based diagrams.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    一方で
    -1.05
    habited
    -1.05
     мою
    -1.01
    我了
    -1.01
     dentaire
    -0.98
    ないで
    -0.93
     haremos
    -0.92
    viève
    -0.92
     permisos
    -0.91
    EMPLOYEE
    -0.90
    POSITIVE LOGITS
     a
    1.26
     similar
    0.96
    低
    0.91
    {\
    0.90
     an
    0.90
     similarly
    0.89
     žaid
    0.88
    Plasmid
    0.86
     šo
    0.86
     mė
    0.85
    Activations Density 0.003%

    No Known Activations