© 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. 41680
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or letters

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

    The neuron fires on standalone numeric tokens (i.e. numbers and digits) 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
     What
    -2.14
    .......
    -2.13
     (
    -2.13
     decadent
    -2.08
     —
    -2.08
    <blockquote>
    -2.05
     From
    -2.05
    .....
    -2.03
     L
    -2.03
     S
    -2.03
    POSITIVE LOGITS
     TÉ
    2.28
     caricatura
    2.25
     plafon
    2.23
    蟊
    2.14
     maniere
    2.11
    癭
    2.11
     bricola
    2.05
     juſ
    2.05
     lavable
    2.05
    雠
    1.99
    Activations Density 0.031%

    No Known Activations