© 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. 58494
    Prev
    Next
    INDEX
    Explanations

    code and markup tags

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

    The neuron detects numeric literals (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
    鱨
    -2.70
     vinil
    -2.55
     perna
    -2.39
     resultat
    -2.38
     camiset
    -2.38
     内衣
    -2.36
     parachoque
    -2.34
     estadounid
    -2.34
     bronz
    -2.34
     pérd
    -2.33
    POSITIVE LOGITS
     
    3.73
     in
    2.91
    </sub>
    2.38
    </strong>
    2.20
    1
    2.17
     It
    2.06
    "
    2.05
    5
    2.03
     For
    1.91
    </u>
    1.90
    Activations Density 0.036%

    No Known Activations