© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64511
    Prev
    Next
    INDEX
    Explanations

    numbers and sequences

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

    The neuron fires on numerical expressions and quantity words (e.g. counts, measurements, frequencies, and related quantifiers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    erobic
    -1.16
    фри
    -1.00
    pullover
    -0.99
    odyne
    -0.99
    枱
    -0.98
     命令
    -0.98
     vermogen
    -0.96
    がなく
    -0.94
    !\!\
    -0.94
     portfolio
    -0.94
    POSITIVE LOGITS
     days
    1.43
     consecutive
    1.30
     Besøkt
    1.23
     visits
    1.23
     successive
    1.20
     rounds
    1.19
    providedIn
    1.15
    vägen
    1.11
     visit
    1.08
     repeated
    1.07
    Activations Density 0.064%

    No Known Activations