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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92712
    Prev
    Next
    INDEX
    Explanations

    environment domain formatter

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

    The neuron fires strongly on programming‐style tokens (identifiers, keywords, paths, etc.) – in other words, it flags code segments rather than natural‐language text.

    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
    ллер
    -0.83
     Ел
    -0.75
     dext
    -0.72
     Nucle
    -0.72
    UMMY
    -0.71
     Warne
    -0.71
    Adaptive
    -0.71
     quán
    -0.70
    addUser
    -0.69
     Elast
    -0.68
    POSITIVE LOGITS
    Environment
    0.99
     Environment
    0.98
    Formatter
    0.95
     formatter
    0.90
     environment
    0.90
    formatter
    0.88
     format
    0.86
     domain
    0.85
    Domain
    0.79
    环境
    0.79
    Activations Density 0.083%

    No Known Activations