© 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. 71246
    Prev
    Next
    INDEX
    Explanations

    template file or definition

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

    The neuron activates on multi‐digit numeric tokens.

    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
     fotball
    -2.56
     dansk
    -2.28
     reise
    -2.14
    🤠
    -2.08
     vuitton
    -2.08
     norsk
    -2.06
     ferien
    -2.02
     sentral
    -2.02
     lyd
    -1.99
     skog
    -1.99
    POSITIVE LOGITS
     you
    1.98
     
    1.97
     and
    1.82
    ↵↵
    1.73
     сделан
    1.71
     fiabilidad
    1.70
    を書く
    1.66
     каждый
    1.61
    を書
    1.60
     ...
    1.57
    Activations Density 0.346%

    No Known Activations