© 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. 98493
    Prev
    Next
    INDEX
    Explanations

    items or tasks followed by specifications

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

    The neuron activates on numeric tokens—digits, numbers (including decimals), measurements, dates, prices, and similar quantity values.

    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
    writeHead
    -1.25
     \%}$
    -1.25
     londres
    -1.11
     therefore
    -1.11
     they
    -1.10
    âni
    -1.10
    ítulo
    -1.09
     поэтому
    -1.08
    𝛼
    -1.05
    ölkerung
    -1.02
    POSITIVE LOGITS
     aprobado
    1.08
     and
    1.06
    浴び
    1.00
    Curs
    0.96
    Pontos
    0.96
    צלחה
    0.95
    Provin
    0.94
    örande
    0.94
     proposto
    0.93
    Descriere
    0.93
    Activations Density 0.003%

    No Known Activations