© 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. 10-GEMMASCOPE-RES-131K
    7. 20356
    Prev
    Next
    INDEX
    Explanations

    participants in studies

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

    The neuron activates on numeric values (counts, percentages, or measurements) appearing in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -2.47
     in
    -1.86
     than
    -1.32
     across
    -1.22
    -
    -1.18
    CFO
    -1.13
    ник
    -1.13
    !
    -1.09
    wakilan
    -1.05
    Ԁ
    -1.04
    POSITIVE LOGITS
     exportaciones
    1.53
     anoche
    1.49
     sufrir
    1.49
    谁能
    1.45
     llorar
    1.43
     duquel
    1.41
     únicamente
    1.34
     bautizo
    1.34
     olvidar
    1.34
     sorpresas
    1.34
    Activations Density 0.157%

    No Known Activations