© 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. 30567
    Prev
    Next
    INDEX
    Explanations

    spec_helper

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

    The neuron fires on the string fragments of file‐path literals in test files—especially on occurrences of “spec”, “_”, and “helper” in require/require_relative lines.

    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
    ローチ
    -0.80
     ढ
    -0.73
    setParameter
    -0.70
    тивно
    -0.69
    pregnant
    -0.66
    SDK
    -0.66
     Shelly
    -0.65
     Chinook
    -0.65
     embryo
    -0.63
     SECRETARY
    -0.63
    POSITIVE LOGITS
     Spec
    0.94
    Spec
    0.91
     spec
    0.85
     SPEC
    0.80
    spec
    0.80
    PECT
    0.77
     speculation
    0.74
    SPEC
    0.71
     Footer
    0.69
     conform
    0.68
    Activations Density 0.057%

    No Known Activations