© 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. 10-GEMMASCOPE-RES-131K
    7. 42296
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols like 'f'

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

    The neuron detects standalone numeric tokens (digits or 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_10/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
    ↵
    -1.69
     the
    -1.36
     also
    -1.34
     yıl
    -1.30
    s
    -1.29
    z
    -1.26
     unnecessarily
    -1.24
    只见
    -1.23
    がない
    -1.23
     
    -1.20
    POSITIVE LOGITS
     they
    1.79
    THEY
    1.56
     ਅਤੇ
    1.48
     близько
    1.45
     Herzens
    1.45
    AMAZING
    1.43
    OCCURRED
    1.42
    Gone
    1.40
     揚げ
    1.38
    ennemi
    1.38
    Activations Density 0.003%

    No Known Activations