© 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. 71501
    Prev
    Next
    INDEX
    Explanations

    events followed by punctuation

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

    The neuron activates on numeric tokens (multi‐digit 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_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
     своем
    -1.04
     (
    -1.01
     vingt
    -0.99
    アレル
    -0.96
    particularly
    -0.96
     Boletín
    -0.94
    q
    -0.94
     apri
    -0.94
    m
    -0.94
     quels
    -0.93
    POSITIVE LOGITS
     last
    1.24
    hhhhh
    1.19
    jobb
    1.16
    rrrrrr
    1.16
    wwwwwwww
    1.14
    😓
    1.11
    hhhhhhhh
    1.11
     poffe
    1.09
     sekarang
    1.07
    jsoup
    1.07
    Activations Density 0.146%

    No Known Activations