© 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. 117899
    Prev
    Next
    INDEX
    Explanations

    technical categories and specific terms

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

    This neuron strongly activates on tokens that occur immediately before numeric data (i.e. words right before 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
     Nearby
    -0.94
     mété
    -0.85
    fillRect
    -0.81
     acronym
    -0.80
     giảng
    -0.78
     ouest
    -0.77
     squat
    -0.75
    ತ
    -0.74
     nearby
    -0.73
    amblea
    -0.73
    POSITIVE LOGITS
    がとても
    0.92
    regardless
    0.79
     nástro
    0.79
     Вікі
    0.78
    💂
    0.77
    Beskrivelse
    0.77
    though
    0.77
    SAFE
    0.75
     цвят
    0.75
    Npc
    0.75
    Activations Density 0.000%

    No Known Activations