© 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. 91950
    Prev
    Next
    INDEX
    Explanations

    Returns async or run

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

    This neuron specializes in spotting programming‐related tokens—like code keywords, method names, and other identifier strings common in source files.

    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
    性が
    -0.96
    auso
    -0.85
     consecuencias
    -0.78
    國內
    -0.78
     travelling
    -0.78
     regimes
    -0.77
    руют
    -0.77
    Its
    -0.77
     gloves
    -0.76
     errors
    -0.75
    POSITIVE LOGITS
     by
    1.13
    ئيه
    0.92
     igenom
    0.86
     främ
    0.79
    ínico
    0.79
     uitgevoerd
    0.78
     största
    0.77
     JsonResponse
    0.76
    чем
    0.74
    deira
    0.74
    Activations Density 0.001%

    No Known Activations