© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35676
    Prev
    Next
    INDEX
    Explanations

    length and time scales

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

    The neuron detects mathematical and scientific notation, such as variables, equations, and numerical expressions.

    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
     ELECTION
    -1.38
     BENE
    -1.33
     ENTERTAINMENT
    -1.29
     undervis
    -1.28
     vixion
    -1.28
     diing
    -1.27
     sesu
    -1.23
     MARKETING
    -1.23
     AllAfrica
    -1.21
     elek
    -1.20
    POSITIVE LOGITS
     even
    1.48
     in
    1.46
     at
    1.46
     initiating
    1.45
     large
    1.41
     small
    1.34
     because
    1.30
     $
    1.30
     our
    1.29
     this
    1.28
    Activations Density 0.023%

    No Known Activations