© 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. 22-GEMMASCOPE-RES-131K
    7. 128374
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric literals (standalone numbers) in code or configuration text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    XML identifiers like flickrid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     regionales
    -0.90
     فقط
    -0.88
    $>
    -0.87
    渕
    -0.86
    檳
    -0.84
    诨
    -0.84
    nthesis
    -0.83
     Purdy
    -0.82
    моро
    -0.82
    aña
    -0.81
    POSITIVE LOGITS
     its
    1.26
     corresponding
    0.99
     соответству
    0.97
    航班
    0.96
    ärs
    0.88
    íram
    0.87
     опять
    0.85
    ⢫
    0.84
     deutlich
    0.84
     entspre
    0.82
    Activations Density 0.006%

    No Known Activations