© 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. 128677
    Prev
    Next
    INDEX
    Explanations

    transcend and transmembrane

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

    The neuron detects the word "transcend" and its variations (transcendental, transcending), with some secondary response to "transmembrane".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ";
    -2.63
    莇
    -2.56
    拊
    -2.52
    </h1>
    -2.50
    </i>
    -2.41
    見つ
    -2.28
    薷
    -2.23
    鴬
    -2.19
    壆
    -2.17
    」。
    -2.16
    POSITIVE LOGITS
    ’
    3.67
    ↵
    2.63
    </em>
    2.52
    诸多
    2.42
    咴
    2.38
    ୌ
    2.38
    𖥦
    2.28
    }{
    2.25
    ～～
    2.22
     $\
    2.19
    Activations Density 0.002%

    No Known Activations