© 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. 84602
    Prev
    Next
    INDEX
    Explanations

    occurrence and spawning

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

    programming and technical content in code files, documentation, or configuration data.

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

    The neuron is activated by curly‐brace characters (“{” and “}”) that mark block delimiters in source code or structured data.

    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
    yethyl
    -0.87
     dłu
    -0.86
     lasts
    -0.81
     neuesten
    -0.75
    校長
    -0.74
     phenolic
    -0.74
     wünschen
    -0.74
    材质
    -0.73
    achet
    -0.73
    inada
    -0.73
    POSITIVE LOGITS
     occurrence
    0.90
    ючи
    0.90
    Spa
    0.85
     occurrences
    0.84
    spa
    0.84
     spawns
    0.82
     spawning
    0.82
    ถม
    0.80
    概率
    0.80
     spawn
    0.79
    Activations Density 0.005%

    No Known Activations