© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35303
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    The neuron detects programming‐related identifier tokens—variable names, class or field names, config keys, etc.—in source code or structured data snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    oría
    -0.88
    dapat
    -0.88
    numbers
    -0.86
    shund
    -0.85
    quando
    -0.85
    ıyordu
    -0.85
    medel
    -0.83
    lük
    -0.82
    picked
    -0.82
    每
    -0.81
    POSITIVE LOGITS
     contactez
    0.98
    Ꮀ
    0.92
     indien
    0.87
     Ahora
    0.86
    quate
    0.86
    jom
    0.85
     выполня
    0.84
    लि
    0.83
     désormais
    0.82
    gaon
    0.81
    Activations Density 0.067%

    No Known Activations