© 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. 112921
    Prev
    Next
    INDEX
    Explanations

    medical patients and physicians

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

    physicians, patients, or advice

    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
    Ja
    0.47
    Jangan
    0.45
    ivi
    0.45
    の新
    0.44
     воро
    0.43
    城的
    0.43
     ভঙ্গ
    0.43
    、
    0.42
    on
    0.42
    のお
    0.41
    POSITIVE LOGITS
     என்பவர்
    0.57
     pediatric
    0.52
     patients
    0.51
     physicians
    0.49
     pacientes
    0.48
     mellitus
    0.48
     médical
    0.48
     রোগীর
    0.48
     चिकित्सा
    0.48
     clinician
    0.48
    Activations Density 0.002%

    No Known Activations