© 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. 30309
    Prev
    Next
    INDEX
    Explanations

    code headers and licenses

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

    The neuron selectively fires on numeric literals (numbers) in code or comments.

    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
    íteni
    -0.86
     tény
    -0.78
    endswith
    -0.77
     gor
    -0.76
    Interop
    -0.75
     contrasted
    -0.75
    jsonPath
    -0.73
     egyszer
    -0.72
     rectum
    -0.72
    ори
    -0.71
    POSITIVE LOGITS
     Preacher
    0.78
     Rens
    0.77
     más
    0.77
    Más
    0.75
    pendicular
    0.74
    baguna
    0.74
    Allgemeine
    0.73
     Aner
    0.72
     corrupción
    0.72
     raggi
    0.72
    Activations Density 0.011%

    No Known Activations