© 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. 36245
    Prev
    Next
    INDEX
    Explanations

    math problem question keywords

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

    This neuron is strongly activated by numeric tokens, especially multi‐digit 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
     from
    -1.64
     with
    -1.54
     for
    -1.50
     first
    -1.41
     on
    -1.39
     strives
    -1.38
     prominent
    -1.36
     simbol
    -1.35
     unrelenting
    -1.34
    嬗
    -1.34
    POSITIVE LOGITS
     wonderfully
    1.93
     hugely
    1.92
     insanely
    1.82
     horrid
    1.77
     exceedingly
    1.74
     incredibly
    1.74
     unbelievably
    1.70
     delightfully
    1.68
     strikingly
    1.68
     ridiculously
    1.68
    Activations Density 0.001%

    No Known Activations