© 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. 104337
    Prev
    Next
    INDEX
    Explanations

    clocked times during tests

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

    The neuron is tuned to pick out numeric tokens (numbers, dates, measurements, and similar statistics) 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_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
     éviter
    -1.13
    descri
    -1.09
     procéder
    -1.09
     requête
    -1.07
    primarily
    -1.02
     empêcher
    -1.02
     hoved
    -1.02
    ᜒ
    -1.01
     Municipalidad
    -1.01
    ständige
    -1.01
    POSITIVE LOGITS
     on
    1.42
     using
    1.37
     at
    1.34
     test
    1.28
     during
    1.27
     various
    1.27
     four
    1.24
     recorded
    1.23
     tests
    1.20
     three
    1.19
    Activations Density 0.017%

    No Known Activations