© 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. 206582
    Prev
    Next
    INDEX
    Explanations

    healthcare and EHR expertise

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

    introducing applications or premise

    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
     derr
    0.47
     compartir
    0.46
     parede
    0.46
    ttemberg
    0.46
    ᄊ
    0.46
     ちゃっ
    0.45
    ಕ್ರಮ
    0.45
     디
    0.44
     সেগুলো
    0.44
    ல்லிய
    0.43
    POSITIVE LOGITS
    Overview
    0.49
    édez
    0.49
    का
    0.47
    (
    0.43
    బడు
    0.41
    ⁵
    0.41
    ЗИ
    0.41
    efore
    0.40
     الفرنسي
    0.40
     observable
    0.39
    Activations Density 0.000%

    No Known Activations