© 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. 57520
    Prev
    Next
    INDEX
    Explanations

    position, size, and orientation

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

    The neuron strongly activates on numeric literals (integer values) 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
     position
    -1.74
    Location
    -1.57
     location
    -1.57
    位置
    -1.55
     위치
    -1.51
     LOCATION
    -1.49
    setPosition
    -1.48
    の位置
    -1.48
     POSITION
    -1.45
    position
    -1.39
    POSITIVE LOGITS
     orientation
    1.02
     radius
    0.94
     size
    0.94
     width
    0.93
     rotation
    0.91
     orienta
    0.90
     angle
    0.90
     direction
    0.85
    orientation
    0.83
    角度
    0.81
    Activations Density 0.026%

    No Known Activations