© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6883
    Prev
    Next
    INDEX
    Explanations

    oval shape or specific entities

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

    The neuron responds to occurrences of the substring “oval” (e.g. in “oval,” “ovalbumin,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     ไม่
    -2.91
     ถ้า
    -2.63
    
    -2.59
    苼
    -2.52
     แต่
    -2.50
    </td>
    -2.50
    贗
    -2.48
    儅
    -2.45
    
    -2.39
     mesmas
    -2.38
    POSITIVE LOGITS
    </strong>
    3.17
    The
    2.53
    a
    2.45
    istically
    2.45
     Extremely
    2.38
    Other
    2.38
    𐐪
    2.38
     facilitating
    2.36
    amp
    2.33
     seamless
    2.30
    Activations Density 0.002%

    No Known Activations