© 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. 22-GEMMASCOPE-RES-131K
    4. 71692
    Prev
    Next
    INDEX
    Explanations

    and then following words

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

    The neuron is triggered by multi‐digit numeric literals (e.g. version numbers, years, counts).

    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
     not
    -2.41
     just
    -2.23
     or
    -2.17
     first
    -2.11
     all
    -2.11
     one
    -1.99
     only
    -1.96
     at
    -1.96
     new
    -1.95
     from
    -1.95
    POSITIVE LOGITS
     Dinas
    2.11
     REALLY
    1.88
     unbelievably
    1.86
     パッド
    1.79
     😁
    1.79
     ludicrous
    1.77
     delightfully
    1.77
     ridiculously
    1.73
     horrid
    1.72
     😊
    1.71
    Activations Density 0.093%

    No Known Activations