© 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. 66404
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    This neuron fires on numeric tokens or multi‐digit number strings.

    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
     who
    -1.27
     Δια
    -1.12
    itária
    -1.11
    icolo
    -1.06
     [{
    -1.05
     [],
    -1.04
    Among
    -1.04
     substantive
    -1.02
    })->
    -1.02
    Nép
    -0.99
    POSITIVE LOGITS
     florales
    1.15
     Wortes
    1.11
     internationaux
    1.07
     regresa
    1.07
     pertinentes
    1.06
     Mitteln
    1.05
     découver
    1.03
     tristes
    1.01
     étr
    1.00
     fraî
    0.98
    Activations Density 0.158%

    No Known Activations