© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19530
    Prev
    Next
    INDEX
    Explanations

    tip, caution, Snowy Night

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

    This neuron responds to numeric literals (especially decimal numbers) 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
    ſſel
    -3.13
    铼
    -3.05
    ⌵
    -3.03
    鲧
    -3.03
    鲼
    -2.86
    屃
    -2.80
    埸
    -2.78
    🫡
    -2.75
    ーズン
    -2.73
    榦
    -2.73
    POSITIVE LOGITS
    0
    3.72
    1
    3.70
    The
    3.23
     Focusing
    3.16
     Approximately
    3.14
     Coupled
    2.98
    2
    2.92
    /
    2.86
     Utilizing
    2.84
    5
    2.84
    Activations Density 0.009%

    No Known Activations