© 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. 111030
    Prev
    Next
    INDEX
    Explanations

    simple geometric shapes

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

    The neuron activates on geometric shape descriptors (e.g., rectangular, square, round, oval, circular).

    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
     spherical
    -1.13
     circular
    -0.93
     linear
    -0.91
    PH
    -0.91
     aware
    -0.90
    三角
    -0.88
     линей
    -0.86
    Circle
    -0.85
    spher
    -0.85
     circulaire
    -0.83
    POSITIVE LOGITS
     shape
    1.98
     shaped
    1.97
    shaped
    1.93
    haped
    1.89
    shape
    1.61
     Shape
    1.45
    形的
    1.44
     Shaped
    1.44
     shapes
    1.39
    Shape
    1.27
    Activations Density 0.081%

    No Known Activations