© 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. 95509
    Prev
    Next
    INDEX
    Explanations

    þ

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

    The neuron reliably activates on numeric tokens (integers or decimals), effectively picking out 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
     mungkin
    -1.14
     amount
    -1.13
     item
    -1.11
     then
    -1.10
    の人に
    -1.08
     range
    -1.06
     that
    -1.05
     likely
    -1.05
     Sloveniji
    -1.05
     may
    -1.02
    POSITIVE LOGITS
     歳
    1.08
     світ
    0.95
     bedient
    0.93
    相反
    0.93
    ｔ
    0.92
    張
    0.90
    这两个
    0.89
    Both
    0.88
    ReferenceEquals
    0.87
     gratifying
    0.87
    Activations Density 0.010%

    No Known Activations