© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10861
    Prev
    Next
    INDEX
    Explanations

    prescription and medications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    杓
    2.36
     роках
    2.32
     obdob
    2.32
    ੭
    2.26
     صہیون
    2.14
    rained
    2.13
    нам
    2.13
    ⣶
    2.12
     بدر
    2.12
    よい
    2.11
    POSITIVE LOGITS
     trade
    1.97
    clus
    1.79
     horse
    1.79
    ges
    1.78
     copy
    1.78
    cil
    1.72
     ret
    1.71
     ley
    1.70
    cussion
    1.70
    bike
    1.70
    Activations Density 0.048%

    No Known Activations