© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8076
    Prev
    Next
    INDEX
    Explanations

    spectral classifications, line, norm, triple, analysis, resolution, ranges, response, properties

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

    The main thing this neuron does is detect occurrences of the word “spectral.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    埽
    -4.06
    
    -3.27
    
    -2.88
    塒
    -2.75
    ㇼ
    -2.70
    ⵔ
    -2.69
    塍
    -2.64
    镦
    -2.61
    抟
    -2.59
    怱
    -2.59
    POSITIVE LOGITS
    3
    3.03
    D
    2.66
    ～～
    2.63
    )
    2.59
    A
    2.55
     consummate
    2.50
    B
    2.50
    K
    2.48
    M
    2.44
    '
    2.44
    Activations Density 0.006%

    No Known Activations