© 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. 34-GEMMASCOPE-RES-131K
    4. 83084
    Prev
    Next
    INDEX
    Explanations

    in compliance with the License

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

    The neuron activates on numeric tokens (number strings) 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
     Vote
    -0.71
     briefs
    -0.68
    しくて
    -0.68
     nocturnal
    -0.68
     hospitalization
    -0.68
    āciju
    -0.67
     after
    -0.67
     nasty
    -0.66
    País
    -0.66
     Centre
    -0.65
    POSITIVE LOGITS
     STO
    0.72
     리
    0.70
    gido
    0.70
     Архиви
    0.69
    iserie
    0.69
    tikan
    0.68
    Willow
    0.68
    Prepare
    0.67
     öğ
    0.66
    روان
    0.66
    Activations Density 0.062%

    No Known Activations