© 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. 16-GEMMASCOPE-2-RES-262K
    7. 117304
    Prev
    Next
    INDEX
    Explanations

    medical terminology and related fields

    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_16_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
    o
    0.58
    “
    0.49
    a
    0.45
    ais
    0.45
    5
    0.44
    ah
    0.44
    1
    0.44
    Temper
    0.43
    A
    0.42
    CEO
    0.42
    POSITIVE LOGITS
     אנ
    0.58
     zina
    0.52
    龧
    0.52
    侾
    0.52
     ಟ
    0.51
    尽快
    0.50
    <unused740>
    0.50
    йдз
    0.50
     žene
    0.50
     vrste
    0.50
    Activations Density 0.000%

    No Known Activations