© 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. 10-GEMMASCOPE-RES-131K
    7. 72528
    Prev
    Next
    INDEX
    Explanations

    structs and bindings

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

    This neuron detects numeric literals (integers and real numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     FOR
    -1.76
    after
    -1.73
    What
    -1.72
    If
    -1.70
    because
    -1.70
    ↵
    -1.59
     It
    -1.59
     ,
    -1.55
     after
    -1.52
    …”
    -1.48
    POSITIVE LOGITS
     asemenea
    1.55
     leſs
    1.54
     ſy
    1.53
    はこの
    1.48
    ientras
    1.48
     psicologia
    1.47
     Politica
    1.45
    鶫
    1.45
    onView
    1.42
     tikai
    1.41
    Activations Density 0.004%

    No Known Activations