© 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. 34-GEMMASCOPE-RES-131K
    7. 109202
    Prev
    Next
    INDEX
    Explanations

    numbers and letters

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

    The neuron selectively activates on numeric tokens (sequences of digits), effectively identifying 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_34/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
     Jego
    -0.78
    şte
    -0.76
    его
    -0.75
    videoId
    -0.73
     огонь
    -0.73
    zące
    -0.73
    quinta
    -0.73
    beck
    -0.73
     lions
    -0.70
     его
    -0.70
    POSITIVE LOGITS
    ributos
    0.90
    CIR
    0.78
     urmă
    0.77
    Tours
    0.74
    龕
    0.73
     dessas
    0.72
    ustes
    0.71
    =((
    0.71
    りの
    0.70
     DEF
    0.69
    Activations Density 0.034%

    No Known Activations