© 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. 34-GEMMASCOPE-RES-131K
    7. 99562
    Prev
    Next
    INDEX
    Explanations

    code documentation and programming snippets

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

    The neuron detects numeric literals (integer tokens) in code and comments.

    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
     maske
    -0.96
    🐯
    -0.88
     medis
    -0.83
     eksper
    -0.82
    Hulu
    -0.81
    jetzt
    -0.79
    Сейчас
    -0.76
    Література
    -0.76
     孔
    -0.76
     lyder
    -0.75
    POSITIVE LOGITS
     $
    0.88
     allerede
    0.84
     Ferner
    0.80
     Mittelalter
    0.77
    kinase
    0.77
    "${
    0.77
     among
    0.75
     znajd
    0.74
    ruz
    0.74
     quidem
    0.74
    Activations Density 0.009%

    No Known Activations