© 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. 32646
    Prev
    Next
    INDEX
    Explanations

    coding or text editing workflows

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

    The neuron fires on programming‐related identifiers (class, package, library, or API names) found in source‐code imports/includes rather than on ordinary 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
    جرة
    -0.73
    phospho
    -0.73
     low
    -0.68
    ophon
    -0.68
     Three
    -0.67
     three
    -0.66
    objects
    -0.66
     dry
    -0.66
     êtes
    -0.63
     good
    -0.63
    POSITIVE LOGITS
     asser
    0.79
    モンド
    0.79
    тч
    0.71
     sprite
    0.70
     tanning
    0.68
    setVisible
    0.68
     HERO
    0.68
     spas
    0.67
    וט
    0.66
     fasteners
    0.66
    Activations Density 0.051%

    No Known Activations