© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10959
    Prev
    Next
    INDEX
    Explanations

    safeguarding against

    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_13_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
    Эти
    1.18
    Этот
    1.16
    О
    1.07
     Также
    1.05
    Эта
    1.04
    гре
    1.04
     Этот
    1.03
     Эти
    1.03
     Эта
    1.02
    Ты
    0.97
    POSITIVE LOGITS
     dê
    1.32
     দুদকের
    1.31
     kē
    1.25
     blushing
    1.23
    ⿸
    1.22
     medals
    1.22
     डाक
    1.22
     mừng
    1.21
     tentatively
    1.20
     wreath
    1.20
    Activations Density 0.000%

    No Known Activations