© 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. 13085
    Prev
    Next
    INDEX
    Explanations

    data transfer and inclusion

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

    The neuron activates on numeric tokens, i.e. multi‐digit strings representing quantities, IDs, dates, or sizes.

    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
    NOTAS
    -1.04
    ToBounds
    -1.02
     この
    -1.01
    RESULTADOS
    -0.99
     ????
    -0.95
    7
    -0.95
     通过
    -0.95
    Luxem
    -0.95
     Umständen
    -0.94
    höhe
    -0.93
    POSITIVE LOGITS
     alongside
    1.92
     in
    1.39
     along
    1.30
     as
    1.29
     साथ
    1.17
     μαζί
    1.15
     included
    1.13
    along
    1.13
     together
    1.13
     함께
    1.13
    Activations Density 0.101%

    No Known Activations