© 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. 21817
    Prev
    Next
    INDEX
    Explanations

    search results and configurations

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

    This neuron detects standalone numeric tokens (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
    哙
    -2.09
    鲽
    -1.95
     手绘
    -1.84
    hiculo
    -1.81
    ᯾
    -1.80
    泐
    -1.76
    艽
    -1.73
     comienzos
    -1.73
    Läs
    -1.72
    鑷
    -1.64
    POSITIVE LOGITS
    in
    2.53
    ar
    2.13
    ↵↵
    2.11
    B
    1.88
    or
    1.83
     \
    1.76
    3
    1.70
     altes
    1.65
    an
    1.59
     eigenes
    1.56
    Activations Density 0.052%

    No Known Activations