© 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. 53953
    Prev
    Next
    INDEX
    Explanations

    program code identifiers

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

    The neuron fires strongly on programming and technical identifiers—class names, annotations, configuration keys, and other code tokens.

    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
    edu
    -0.84
    ');
    -0.83
    ],
    -0.80
     ide
    -0.77
    <![
    -0.76
     ६
    -0.76
    '));
    -0.76
     صوتيه
    -0.75
    Вт
    -0.74
     reembolso
    -0.73
    POSITIVE LOGITS
    École
    0.88
     lla
    0.83
    TÜ
    0.81
     sampler
    0.80
     Trường
    0.77
    urgy
    0.77
    Moc
    0.76
    bedarf
    0.75
     FLAG
    0.75
    Quartz
    0.75
    Activations Density 0.001%

    No Known Activations