© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 205503
    Prev
    Next
    INDEX
    Explanations

    doctor triaging patient emails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rubber
    0.45
    rubber
    0.39
    encryption
    0.39
    elics
    0.38
    __.
    0.37
    awi
    0.36
     rubber
    0.36
    Gal
    0.36
    cud
    0.36
    Def
    0.35
    POSITIVE LOGITS
     уже
    0.47
    笘
    0.46
     distribute
    0.44
     вже
    0.44
    鐩
    0.42
     כבר
    0.42
     ګرځ
    0.39
     contrôle
    0.39
    笊
    0.39
    کت
    0.39
    Activations Density 0.005%

    No Known Activations