© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7043
    Prev
    Next
    INDEX
    Explanations

    sulfur and phosphorus compounds

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

    sulfur compounds

    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_53_width_65k_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
     ކުރ
    0.39
     hydrostatic
    0.38
    apabb
    0.38
     पदाधिकारी
    0.38
    秾
    0.37
     በመ
    0.37
    쁘
    0.37
     लगाएं
    0.37
     Fellowship
    0.36
    执
    0.36
    POSITIVE LOGITS
    ated
    0.73
    ates
    0.69
    化物
    0.68
    ate
    0.64
    ATED
    0.64
    ATE
    0.63
     dioxide
    0.63
    ATES
    0.63
     Dioxide
    0.61
    urous
    0.59
    Activations Density 0.020%

    No Known Activations