© 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. 1064
    Prev
    Next
    INDEX
    Explanations

    technical compound terms

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

    This neuron responds to code identifier tokens—especially segments of CamelCase or underscored names (e.g. “Bare”, “metal”, “third_party”, “External”, “Code_Coverage”).

    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
     some
    -1.05
     all
    -0.98
     everything
    -0.96
     with
    -0.95
     both
    -0.91
     just
    -0.89
     Kolon
    -0.87
     first
    -0.85
     also
    -0.85
    peč
    -0.85
    POSITIVE LOGITS
     olika
    1.21
    為に
    0.98
     établie
    0.97
    ***************/
    0.97
    oka
    0.96
     Bereiche
    0.95
     arcane
    0.95
    mögens
    0.94
     taką
    0.94
    cey
    0.94
    Activations Density 0.045%

    No Known Activations