© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6296
    Prev
    Next
    INDEX
    Explanations

    paths, URLs, locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    咛
    1.19
     прия
    1.16
    愉快
    1.08
     الطيب
    1.05
     дітей
    1.05
     menyenangkan
    1.04
     kalangan
    1.02
    蛀
    1.01
    ths
    1.00
     जीबी
    0.99
    POSITIVE LOGITS
     eSIM
    1.73
     unlock
    1.53
    iscale
    1.50
    óság
    1.48
    undefined
    1.47
    Ấ
    1.46
    ularis
    1.45
    iddish
    1.45
    يجي
    1.45
    ikation
    1.45
    Activations Density 0.018%

    No Known Activations