© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124580
    Prev
    Next
    INDEX
    Explanations

    restaurant business and industry

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

    the presence of the word “restaurant” (in singular or plural form) in the text.

    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
     we
    -2.88
     dà
    -2.23
    鲞
    -2.16
    苤
    -2.11
    子里
    -2.05
     aspetta
    -2.03
    饪
    -2.02
    潆
    -2.02
     negozio
    -2.02
     但
    -2.02
    POSITIVE LOGITS
    齷
    2.13
    Usually
    2.09
    Typically
    2.08
    哢
    2.06
     ”
    2.03
    Таким
    1.98
    後期
    1.95
     Usually
    1.93
    狆
    1.89
    ’’
    1.88
    Activations Density 0.005%

    No Known Activations