© 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. 67630
    Prev
    Next
    INDEX
    Explanations

    legal citation or sentence start

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

    The neuron activates on multi-digit numeric tokens (e.g. page or line 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_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
    1
    -3.73
    2
    -3.17
    鉝
    -2.67
    0
    -2.66
     (
    -2.59
    -
    -2.44
    3
    -2.42
     is
    -2.41
     to
    -2.39
     I
    -2.19
    POSITIVE LOGITS
    ;
    2.44
     iedere
    2.44
     goederen
    2.39
    幛
    2.36
    ⌵
    2.36
     certificados
    2.33
     conductores
    2.30
    它们
    2.30
    ";
    2.28
    ;'>
    2.22
    Activations Density 0.002%

    No Known Activations