© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5608
    Prev
    Next
    INDEX
    Explanations

    clinical entities and assertion statuses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     foresight
    1.15
     bauen
    1.11
    ຫຼື
    1.08
    centro
    1.08
     Sebab
    1.06
    ຮູ້
    1.05
    ២
    1.05
     fostering
    1.03
     ढंग
    1.03
    न्देल
    1.03
    POSITIVE LOGITS
    ان
    1.64
    ל
    1.55
    '
    1.48
    ’
    1.45
    न
    1.34
    ian
    1.30
    ী
    1.28
    ো
    1.24
    Date
    1.20
    ời
    1.20
    Activations Density 19.313%

    No Known Activations