© 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. 99024
    Prev
    Next
    INDEX
    Explanations

    pagination, register, controls

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

    The neuron activates on numeric tokens (i.e. any standalone 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
    graaf
    -0.93
    diario
    -0.77
     waits
    -0.75
    ;#
    -0.73
     jendela
    -0.72
    artamento
    -0.71
     Waits
    -0.68
    danger
    -0.68
    break
    -0.68
     Bitmap
    -0.68
    POSITIVE LOGITS
     controls
    1.02
     control
    0.90
     Control
    0.82
     Controls
    0.82
     buttons
    0.81
    Controls
    0.81
     Street
    0.80
     UI
    0.79
    Control
    0.79
     Steuerung
    0.77
    Activations Density 0.008%

    No Known Activations