© 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. 66070
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

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

    The neuron activates on numeric literals (integers or decimals) in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    tersebut
    -0.95
    ücher
    -0.92
     Recu
    -0.91
    CLAIMER
    -0.88
    égories
    -0.85
    apollo
    -0.84
    şem
    -0.83
    ühungen
    -0.83
     Punjabi
    -0.82
    gevens
    -0.81
    POSITIVE LOGITS
    團隊
    0.76
     Through
    0.75
     截图
    0.73
    を行います
    0.71
    使って
    0.71
    トレーニング
    0.70
    brada
    0.68
     …
    0.68
     battaglia
    0.67
    透過
    0.66
    Activations Density 0.044%

    No Known Activations