© 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. 110701
    Prev
    Next
    INDEX
    Explanations

    digit 6

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

    The neuron is keyed to numeric tokens, i.e. it fires strongly on individual digits or digit‐only sequences 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
    ar
    -2.69
    TryDecode
    -2.47
     \
    -2.41
    龵
    -2.38
     besonderes
    -2.38
     a
    -2.36
     diligently
    -2.33
    徧
    -2.28
     juega
    -2.25
    咵
    -2.25
    POSITIVE LOGITS
        
    2.47
     dibandingkan
    2.36
     It
    2.31
    は
    2.19
     These
    2.14
    婞
    2.02
    Somebody
    2.02
     знали
    1.98
     signifikan
    1.98
    騭
    1.97
    Activations Density 0.016%

    No Known Activations