© 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. 38676
    Prev
    Next
    INDEX
    Explanations

    Pro titles and labels

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

    The neuron detects the token “Pro” (often capitalized) when it appears as part of product or model names.

    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
     Their
    -2.39
    盦
    -2.38
    <bos>
    -2.19
    ↵↵
    -2.05
    すっきり
    -1.96
     フェイス
    -1.92
    锖
    -1.91
     composição
    -1.88
    🡺
    -1.88
     シート
    -1.88
    POSITIVE LOGITS
     evident
    2.28
    軚
    2.19
     mulut
    2.19
    udadera
    2.17
    u
    2.16
    ा
    2.16
     sebagai
    2.14
     lancia
    2.11
    }$
    2.06
     dari
    2.03
    Activations Density 0.018%

    No Known Activations