© 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. 23816
    Prev
    Next
    INDEX
    Explanations

    image paths and graphic elements

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

    The neuron primarily detects numeric tokens—standalone digits or numbers embedded in 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
    VideoCapture
    -0.82
    rouvez
    -0.74
     dejo
    -0.73
    看了
    -0.71
     instalar
    -0.71
    Wizard
    -0.71
     ASH
    -0.70
    נה
    -0.70
    inhard
    -0.69
    øl
    -0.69
    POSITIVE LOGITS
     Rectangle
    1.42
    Group
    1.36
    Rectangle
    1.35
     Group
    1.30
     rectangle
    1.29
     group
    1.12
    group
    1.10
     rectangles
    1.10
     Shape
    1.00
    Shape
    0.98
    Activations Density 0.010%

    No Known Activations