© 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. 68495
    Prev
    Next
    INDEX
    Explanations

    key-value pairs separated by delimiters

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

    This neuron fires on numeric tokens—particularly standalone numbers and numeric measurements.

    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
     OGSÅ
    -1.57
     kader
    -1.48
    tainment
    -1.45
     konsult
    -1.45
     programmet
    -1.43
    ofern
    -1.41
     gruppen
    -1.41
    ised
    -1.41
    了下去
    -1.40
    gaande
    -1.40
    POSITIVE LOGITS
     in
    1.83
     from
    1.63
     not
    1.55
     to
    1.48
     (
    1.45
    ？　
    1.38
     now
    1.34
     same
    1.31
     thankfully
    1.28
     near
    1.24
    Activations Density 0.045%

    No Known Activations