© 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. 92569
    Prev
    Next
    INDEX
    Explanations

    3D graphics scene components

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

    The neuron activates on code‐style identifiers and literals—e.g. class or file names, type names, extensions, and numeric constants in source code.

    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
    camera
    -0.79
     verhe
    -0.79
    相机
    -0.77
    ιώ
    -0.74
     cameras
    -0.73
     gutters
    -0.73
    cameras
    -0.72
    Cameras
    -0.72
    VertexBuffer
    -0.71
     الرس
    -0.70
    POSITIVE LOGITS
     sphere
    1.19
     plane
    1.15
     floor
    1.02
    Tea
    1.02
     box
    0.90
     tea
    0.88
    sphere
    0.86
     wood
    0.85
     esfera
    0.85
     earth
    0.83
    Activations Density 0.042%

    No Known Activations