© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70912
    Prev
    Next
    INDEX
    Explanations

    numbers, ratings, scores

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

    The neuron strongly activates on standalone numeric tokens (digits and simple numbers) in the text.

    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
     ukraine
    -1.16
    pergillus
    -1.16
     célé
    -1.16
     ketones
    -1.15
    
    -1.14
    
    -1.13
    machte
    -1.12
     nélk
    -1.12
     Процитовано
    -1.11
    każ
    -1.10
    POSITIVE LOGITS
     to
    1.39
     it
    1.25
     had
    1.17
    G
    1.16
    S
    1.15
     as
    1.15
    In
    1.14
     re
    1.11
     two
    1.06
    with
    1.06
    Activations Density 0.058%

    No Known Activations