© 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. 5108
    Prev
    Next
    INDEX
    Explanations

    chemical compounds ending in ate or ine

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

    chemical compounds and elements

    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
    股东
    0.45
    创业
    0.44
    赎
    0.44
     счастли
    0.43
     территория
    0.43
    财政
    0.43
    谄
    0.43
    营业
    0.42
    贰百
    0.42
    上涨
    0.42
    POSITIVE LOGITS
     potassium
    0.49
     sodium
    0.48
     chloride
    0.47
     dimethyl
    0.47
     phosphate
    0.47
     acid
    0.46
     magnesium
    0.45
     hydroxyl
    0.45
     soluble
    0.45
     hydroxide
    0.44
    Activations Density 0.211%

    No Known Activations