© 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-16K
    7. 7055
    Prev
    Next
    INDEX
    Explanations

    biological or medical 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/layer_31_width_16k_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
    Resolved
    0.50
    整個
    0.49
     configuración
    0.48
    Floating
    0.48
    Value
    0.47
    要素
    0.46
    util
    0.45
    値
    0.45
    Glob
    0.45
    全局
    0.45
    POSITIVE LOGITS
     alleles
    0.57
     hypoallergenic
    0.55
     blood
    0.54
     allergies
    0.53
     femur
    0.53
     mell
    0.52
     chores
    0.52
     haem
    0.51
     ankles
    0.51
     haircuts
    0.51
    Activations Density 0.381%

    No Known Activations