© 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. 116785
    Prev
    Next
    INDEX
    Explanations

    KD trees, spatial queries

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

    The neuron primarily activates on numeric tokens (digits and 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
    Varios
    -0.90
    Contexto
    -0.77
    farlane
    -0.73
    Claro
    -0.72
    AtEndOf
    -0.71
    OBJETIVOS
    -0.70
    Objetivos
    -0.70
    smoke
    -0.68
    vertrag
    -0.67
     execução
    -0.66
    POSITIVE LOGITS
     bbox
    0.98
     mort
    0.94
    矩
    0.91
     KD
    0.90
     Subdivision
    0.84
     subdivision
    0.81
    Point
    0.81
     leaf
    0.80
     box
    0.78
    Query
    0.78
    Activations Density 0.014%

    No Known Activations