© 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. 71783
    Prev
    Next
    INDEX
    Explanations

    what other or what else

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

    The neuron primarily detects the word “other” (as in “what other … do you …”) in questions.

    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
     with
    -1.80
     to
    -1.78
     dritte
    -1.70
    );
    -1.59
     difp
    -1.48
    鏐
    -1.48
     氏
    -1.47
    鹛
    -1.47
    ");
    -1.46
     viaja
    -1.46
    POSITIVE LOGITS
    0
    1.91
    a
    1.77
    7
    1.66
    ほか
    1.59
     betrifft
    1.59
     occupe
    1.57
    INE
    1.57
     thing
    1.56
    丝毫
    1.55
    6
    1.54
    Activations Density 0.006%

    No Known Activations