© 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. 34-GEMMASCOPE-RES-131K
    4. 55772
    Prev
    Next
    INDEX
    Explanations

    code delimiters like # encoding or <? xml

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

    This neuron activates on programming‐style text—detecting code fragments and code‐like tokens (e.g. identifiers, keywords, punctuation) rather than natural language.

    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
     ه
    -0.75
     alignItems
    -0.73
    ->
    -0.73
    엣
    -0.71
    ensas
    -0.71
     läuft
    -0.71
    щё
    -0.71
     Plugin
    -0.71
     моби
    -0.71
    ugier
    -0.70
    POSITIVE LOGITS
    rval
    0.91
     Radeon
    0.91
    countDown
    0.84
     Mysore
    0.81
     rval
    0.80
    testnet
    0.80
     monitoring
    0.77
    monitoring
    0.77
     旗
    0.76
    theid
    0.75
    Activations Density 0.029%

    No Known Activations