© 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. 34-GEMMASCOPE-RES-131K
    7. 2387
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    This neuron fires on multi-digit numeric tokens, especially numbers used in citations (years, page or volume numbers, identifiers).

    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
     by
    -1.62
     from
    -1.30
     in
    -1.26
     it
    -1.22
     on
    -1.20
     because
    -1.20
     During
    -1.19
     Since
    -1.14
     At
    -1.14
     There
    -1.13
    POSITIVE LOGITS
    ↵↵
    1.27
     revamped
    1.24
     tumultuous
    1.19
    ౧
    1.15
     funciones
    1.12
     boister
    1.12
     flashy
    1.11
    Mvh
    1.09
     horrifying
    1.09
     captivating
    1.09
    Activations Density 0.002%

    No Known Activations