© 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. 15162
    Prev
    Next
    INDEX
    Explanations

    names of people and places

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

    The neuron activates on numeric tokens (numbers and numerical expressions) in the 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_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
    al
    -2.67
     nimmt
    -2.63
    ଝ
    -2.59
    榖
    -2.59
    
    -2.58
    ﱠ
    -2.56
    栁
    -2.55
    槩
    -2.53
    遢
    -2.53
    geſ
    -2.48
    POSITIVE LOGITS
    .
    3.72
    壜
    3.38
    >
    3.00
    0
    2.92
     Other
    2.56
     verbess
    2.48
    ."
    2.47
    闥
    2.44
     häufigsten
    2.38
     Änderung
    2.31
    Activations Density 0.102%

    No Known Activations