© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83244
    Prev
    Next
    INDEX
    Explanations

    gastronomy, foreign, multilingual

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

    concepts or explanations following certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ற்றிய
    0.48
    در
    0.47
    //
    0.45
    더
    0.45
     Fläche
    0.44
    了一种
    0.42
    Stephen
    0.42
    敀
    0.42
    щих
    0.42
    밭
    0.42
    POSITIVE LOGITS
     gastronomy
    0.58
     வால்பேப்பர்கள்
    0.57
     festivities
    0.56
     wisata
    0.50
     காட்சிகள்
    0.49
     動画
    0.49
    onesian
    0.48
     идти
    0.47
     stomach
    0.47
    SIAN
    0.46
    Activations Density 0.001%

    No Known Activations