© 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. 22-GEMMASCOPE-RES-131K
    7. 73925
    Prev
    Next
    INDEX
    Explanations

    past tense verbs across languages

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

    The neuron fires on numeric tokens (including integers and decimals) 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_22/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
     your
    -2.20
    目前的
    -2.00
     jedem
    -1.84
    㐂
    -1.83
     whats
    -1.81
    》。
    -1.79
    嬗
    -1.77
    Ꭳ
    -1.76
     شیپور
    -1.73
     positivas
    -1.73
    POSITIVE LOGITS
    .
    2.11
    [
    1.95
    2
    1.93
     volna
    1.90
    蹋
    1.88
     originally
    1.88
    も
    1.81
    s
    1.80
    1
    1.76
    ’
    1.76
    Activations Density 0.007%

    No Known Activations