© 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. 22-GEMMASCOPE-RES-131K
    7. 35270
    Prev
    Next
    INDEX
    Explanations

    representing or symbolizing

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

    The main thing this neuron does is pick out words describing visual or spatial design elements (like objects, shapes, orientations, and materials).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    得不
    -1.06
    Elena
    -1.03
     Besoin
    -1.00
     Sünden
    -0.97
     Estudiantes
    -0.96
    ֶּ
    -0.95
    multicolumn
    -0.94
    姫
    -0.93
     bataille
    -0.92
     inimigos
    -0.91
    POSITIVE LOGITS
    代表
    1.75
     represents
    1.60
     representing
    1.59
     symbolizes
    1.36
     represent
    1.36
     symbol
    1.32
     representar
    1.30
    Represents
    1.28
     our
    1.27
    表示
    1.23
    Activations Density 0.023%

    No Known Activations