© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26884
    Prev
    Next
    INDEX
    Explanations

    code keywords

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

    The neuron activates on numeric literal tokens, especially decimal (floating‐point) 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_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
     """",
    -1.26
     (
    -1.18
    Ÿ
    -1.10
    ≅
    -1.07
    ̴
    -1.07
     how
    -1.06
    魇
    -1.05
    templateUrl
    -1.04
    foreignKey
    -1.03
    ЖИ
    -1.03
    POSITIVE LOGITS
     and
    1.42
     öffentlichen
    1.10
    Velocidad
    1.09
    woners
    1.08
    了一些
    1.08
     verschill
    1.08
    諄
    1.06
     hetzelfde
    1.05
     verschillende
    1.00
     Ländern
    1.00
    Activations Density 0.033%

    No Known Activations