© 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. 34-GEMMASCOPE-RES-131K
    4. 47976
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron activates on numeric tokens, i.e. sequences of digits (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_34/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
     గ
    -0.75
    wavering
    -0.74
     Iterable
    -0.73
    Geografi
    -0.73
    rictions
    -0.73
    Verse
    -0.73
     Lösung
    -0.73
    ]-[
    -0.72
     Ir
    -0.71
    Malloc
    -0.71
    POSITIVE LOGITS
     rah
    0.93
     Wexford
    0.82
    itudinal
    0.81
     tekno
    0.77
     PREV
    0.76
    Displacement
    0.75
    ustand
    0.73
     Fixation
    0.72
    ського
    0.71
     spezi
    0.71
    Activations Density 0.008%

    No Known Activations