© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 65111
    Prev
    Next
    INDEX
    Explanations

    medical and biological terms

    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_all/layer_41_width_262k_l0_big
    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
     creases
    0.48
     หัว
    0.46
     শীর্ষ
    0.45
     seams
    0.45
     ridges
    0.44
     frontage
    0.43
    橥
    0.43
     swells
    0.42
    ዋ
    0.42
     piercings
    0.41
    POSITIVE LOGITS
     immune
    0.46
    affected
    0.46
    rologic
    0.46
     affected
    0.44
     रोगी
    0.41
     pharmacokinetic
    0.41
     excret
    0.41
     cytoskeleton
    0.41
     paziente
    0.41
     afectado
    0.40
    Activations Density 0.008%

    No Known Activations