© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110576
    Prev
    Next
    INDEX
    Explanations

    respectively

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

    The neuron activates on numeric tokens (integers or decimal numbers), i.e. any standalone numbers.

    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
    ings
    -1.42
     would
    -1.35
     "
    -1.27
    かの
    -1.23
    厘米
    -1.21
    ské
    -1.20
     is
    -1.19
     когда
    -1.17
     waar
    -1.16
    空调
    -1.16
    POSITIVE LOGITS
     fühlt
    1.41
    umblr
    1.40
     diferenças
    1.39
    About
    1.37
     کردیم
    1.35
    colori
    1.30
     richtet
    1.29
    嚓
    1.28
     geschieht
    1.27
    cibo
    1.27
    Activations Density 0.015%

    No Known Activations