© 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. 9695
    Prev
    Next
    INDEX
    Explanations

    Denmark

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

    The neuron responds strongly to numeric and quantitative tokens (e.g. numerals, numeric modifiers, and related measurement terms).

    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
    ٓ
    -0.92
     competi
    -0.87
     dizziness
    -0.84
    cognito
    -0.83
    urusan
    -0.79
     Dizziness
    -0.78
    矚
    -0.77
    cdb
    -0.75
     dancers
    -0.75
    सार
    -0.75
    POSITIVE LOGITS
     contratto
    1.00
     cambiamento
    0.95
     paziente
    0.93
     ceasing
    0.92
     aggiorn
    0.90
     programação
    0.90
     domani
    0.88
     settore
    0.88
     pomeriggio
    0.87
    无数
    0.86
    Activations Density 0.015%

    No Known Activations