© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30563
    Prev
    Next
    INDEX
    Explanations

    variable value and data types

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

    This neuron fires on programming-related technical terms—especially language names (e.g. “JavaScript,” “Python”), data-structure names (“Set,” “Iterator”), and other code-concept keywords.

    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
    lfloor
    -0.86
     lively
    -0.85
    벡터
    -0.84
    币
    -0.78
    Fiche
    -0.78
    Effectiveness
    -0.77
    FOTOS
    -0.76
    ၈
    -0.75
     wickets
    -0.75
     councils
    -0.74
    POSITIVE LOGITS
     maniere
    1.10
     fondamental
    1.05
     alho
    0.97
     déchets
    0.94
    contained
    0.91
    ISCH
    0.91
     roba
    0.91
     mue
    0.91
    ulators
    0.88
     espr
    0.88
    Activations Density 0.235%

    No Known Activations