© 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. 31-GEMMASCOPE-2-RES-262K
    7. 1683
    Prev
    Next
    INDEX
    Explanations

    diabetes, high blood pressure, weight loss

    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_31_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
    ртуа
    0.21
    掎
    0.21
    Ꮬ
    0.21
    берриз
    0.20
    .",[
    0.20
     রক্ষণ
    0.20
    atthanam
    0.19
    堞
    0.19
     saddhim
    0.19
    ائیگی
    0.19
    POSITIVE LOGITS
    in
    0.26
    K
    0.25
     to
    0.24
    2
    0.24
    m
    0.24
    3
    0.24
    to
    0.23
     be
    0.23
    7
    0.23
    f
    0.23
    Activations Density 0.000%

    No Known Activations