© 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. 161972
    Prev
    Next
    INDEX
    Explanations

    clinical medical health infection

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

    change, diversified, reflecting, identity, cultural

    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
     প্রভৃতির
    0.55
    कांक्षा
    0.50
     જ્યાં
    0.50
     নির্দিষ্ট
    0.46
     दूसरों
    0.46
     phrases
    0.46
    '=
    0.46
     उठता
    0.44
    အစိတ်အပိုင်း
    0.44
     ['(?
    0.44
    POSITIVE LOGITS
     Bloom
    0.55
     Blooming
    0.46
     Supervision
    0.46
     মেডিকেল
    0.43
     Health
    0.43
     Clinical
    0.43
    obaan
    0.43
     Design
    0.42
     infection
    0.42
     Woodward
    0.42
    Activations Density 0.001%

    No Known Activations