© 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. 34-GEMMASCOPE-RES-131K
    7. 103172
    Prev
    Next
    INDEX
    Explanations

    places and events

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

    The neuron specializes in spotting numeric tokens and numerical expressions (digits, numbers, and related symbols).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Californian
    -1.51
     learnt
    -1.30
     hitherto
    -1.29
     envisaged
    -1.27
     spoilt
    -1.11
    NoOf
    -1.05
     Hispanics
    -1.04
     Hispanic
    -1.04
     nowadays
    -1.03
     Mexicans
    -1.02
    POSITIVE LOGITS
     futbol
    1.29
     heretofore
    1.23
     laborers
    1.23
     Parliament
    1.21
     flavorful
    1.20
     awhile
    1.18
    Supplemental
    1.16
     rumored
    1.16
     utilizing
    1.15
     countrymen
    1.14
    Activations Density 0.305%

    No Known Activations