© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49138
    Prev
    Next
    INDEX
    Explanations

    spiral shapes or structures

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

    The neuron fires whenever the text mentions spiral or helical forms (e.g. “spiral,” “spirally,” “helical,” “helically”).

    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
    ඳ
    -0.71
    𝕡
    -0.70
    Triangles
    -0.69
    のです
    -0.69
     Stones
    -0.68
    scat
    -0.67
     سای
    -0.67
    ाषा
    -0.66
     shaking
    -0.66
    ابر
    -0.66
    POSITIVE LOGITS
     spiral
    3.09
     spirals
    2.61
     spir
    2.56
     Spiral
    2.52
     coiled
    2.47
    Spiral
    2.45
     helix
    2.36
     coil
    2.34
     coils
    2.30
    spiral
    2.27
    Activations Density 0.090%

    No Known Activations