© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92773
    Prev
    Next
    INDEX
    Explanations

    point coordinates and objects

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

    The neuron strongly activates on numeric literals (number tokens) in code snippets.

    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
    的机会
    -0.78
    hoben
    -0.72
     apostar
    -0.69
    ใหญ่
    -0.69
     Gid
    -0.69
    敍
    -0.69
    iosa
    -0.68
     Trauer
    -0.67
     Editable
    -0.67
    bet
    -0.66
    POSITIVE LOGITS
     point
    1.36
     Point
    1.34
     POINT
    1.26
    Point
    1.25
     punto
    1.23
     pt
    1.23
    POINT
    1.19
     CGPoint
    1.18
    point
    1.07
    CGPoint
    0.94
    Activations Density 0.026%

    No Known Activations