© 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. 127956
    Prev
    Next
    INDEX
    Explanations

    questions and elephant shark

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

    This neuron activates on numeric tokens (particularly decimal numbers) in mathematical expressions.

    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
    0
    -2.69
    ⼥
    -2.53
    有些不
    -2.39
    梠
    -2.34
    ༛
    -2.33
    o
    -2.30
     με
    -2.27
     животные
    -2.23
    鸶
    -2.23
    蛱
    -2.20
    POSITIVE LOGITS
     There
    2.72
     builds
    2.39
    讴
    2.30
     While
    2.28
     has
    2.27
     selben
    2.25
    
    2.22
    一起来
    2.22
    ay
    2.17
     Besides
    2.16
    Activations Density 0.007%

    No Known Activations