© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32564
    Prev
    Next
    INDEX
    Explanations

    sports statistics, times, or dates

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

    The neuron activates on numeric tokens and figures—i.e. digits or numbers used in statistical, score, or quantitative data.

    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
    ପ
    -0.88
     árbitro
    -0.77
    鏞
    -0.75
    Workout
    -0.74
    PLOT
    -0.73
    ្រ
    -0.71
    gation
    -0.71
     meshes
    -0.70
     अला
    -0.70
    pores
    -0.70
    POSITIVE LOGITS
     bat
    1.03
     plate
    0.97
     up
    0.90
     stepping
    0.82
    公式
    0.81
     petitioned
    0.81
    PLATE
    0.79
     घ
    0.79
     opportunities
    0.78
     appearances
    0.77
    Activations Density 0.014%

    No Known Activations