© 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. 73531
    Prev
    Next
    INDEX
    Explanations

    motto or slogan

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

    This neuron detects occurrences of words like “motto” or “slogan” (often in headings) that introduce a catchphrase or tagline.

    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
    wiście
    -1.72
    nému
    -1.65
    結婚式
    -1.56
     всички
    -1.55
    jelaskan
    -1.50
     with
    -1.49
     duradero
    -1.48
    nemers
    -1.48
     могат
    -1.45
     можуть
    -1.45
    POSITIVE LOGITS
     “
    1.84
    </i>
    1.83
    to
    1.66
    .”
    1.53
    ;
    1.53
    ৩
    1.45
     只
    1.45
     devraient
    1.43
    re
    1.41
    できるだけ
    1.39
    Activations Density 0.021%

    No Known Activations