© 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. 93022
    Prev
    Next
    INDEX
    Explanations

    hairstyle, trade, or technique

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

    The neuron strongly activates on numbers, measurements, dates, and specialized technical or domain-specific terms (e.g. phenomenon names, craft names, numerical values).

    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
     вместо
    -1.13
    Built
    -1.10
    String
    -1.02
    ַל
    -1.02
    January
    -1.01
    Ajax
    -1.01
    ując
    -0.99
     experien
    -0.98
    VIN
    -0.97
     errone
    -0.97
    POSITIVE LOGITS
     used
    1.55
     decades
    1.40
     technique
    1.38
     widely
    1.32
     centuries
    1.16
     practiced
    1.09
     kdy
    1.09
    用到
    1.09
    *}[
    1.09
    ффек
    1.08
    Activations Density 0.132%

    No Known Activations