© 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. 219377
    Prev
    Next
    INDEX
    Explanations

    carbon compounds and chemical names

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

    Carbon / Carbohydrates

    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
    ยัง
    0.47
    andung
    0.46
    зок
    0.46
     ก็
    0.45
    atiti
    0.45
    ๙
    0.44
    ismo
    0.44
     følgende
    0.44
    кия
    0.44
    ontiti
    0.44
    POSITIVE LOGITS
     carbohydrates
    0.52
    萎
    0.47
     Carbon
    0.46
     Sne
    0.46
    两国
    0.45
    碳
    0.45
     carbonates
    0.45
     Carbohyd
    0.45
     Athens
    0.44
     carbs
    0.44
    Activations Density 0.000%

    No Known Activations