© 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. 38700
    Prev
    Next
    INDEX
    Explanations

    spatial and color attributes

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

    The neuron fires on code identifiers that name API calls or object properties (e.g. “position”, “rect”, “textureCoordinate”, “gl_FragColor”).

    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
     chances
    -0.83
    ⋉
    -0.77
     desarrolló
    -0.74
    ∋
    -0.73
    わから
    -0.73
    ваемых
    -0.73
     celebró
    -0.71
     entende
    -0.70
     działalności
    -0.70
     understands
    -0.70
    POSITIVE LOGITS
     tsp
    0.85
    print
    0.79
    डे
    0.77
    PAREN
    0.77
    ADOR
    0.75
    .$
    0.74
    لل
    0.74
    ivotopis
    0.74
    unun
    0.73
    ち
    0.73
    Activations Density 0.016%

    No Known Activations