© 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. 66454
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

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

    The neuron detects numeric tokens—sequences of digits (e.g. prices, 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
     dominante
    -0.98
     into
    -0.97
    onalds
    -0.93
     vider
    -0.91
     उपलब्ध
    -0.90
    issauga
    -0.90
     strass
    -0.86
    としての
    -0.86
     bruto
    -0.85
     paillettes
    -0.85
    POSITIVE LOGITS
     dotyczy
    1.26
     cases
    1.20
     flere
    1.16
     cuya
    1.15
     deportivas
    1.13
     komplette
    1.13
     individuals
    1.09
    είτε
    1.07
     ряда
    1.06
    konstruktion
    1.05
    Activations Density 0.036%

    No Known Activations