© 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. 48249
    Prev
    Next
    INDEX
    Explanations

    numbers and years

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

    The neuron strongly activates on numeric tokens (years, IDs, measurements, and other standalone numbers).

    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
     dahulu
    -0.74
    🪱
    -0.74
     золота
    -0.73
     amarillo
    -0.73
    燚
    -0.72
     Bagian
    -0.72
    iffen
    -0.71
    angkutan
    -0.70
     extensive
    -0.70
     złota
    -0.70
    POSITIVE LOGITS
    hage
    0.79
     flexion
    0.79
    anasia
    0.75
     ballads
    0.75
     Suche
    0.75
     Directeur
    0.73
    uksessa
    0.73
    gives
    0.72
    ErrorMsg
    0.71
     ƙ
    0.71
    Activations Density 0.003%

    No Known Activations