© 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. 16078
    Prev
    Next
    INDEX
    Explanations

    Hold up

    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
    uvi
    1.21
    unia
    1.17
     post
    1.16
    post
    1.15
    ソフトウェア
    1.14
    ellington
    1.14
     maca
    1.12
    꼭
    1.11
     docks
    1.10
    pe
    1.09
    POSITIVE LOGITS
    rishna
    1.27
    Density
    1.23
    UserId
    1.21
    ين
    1.19
    नीकरण
    1.19
    Subscriber
    1.19
     modifié
    1.18
    መስ
    1.17
     اجازت
    1.17
    ර්ථ
    1.16
    Activations Density 0.000%

    No Known Activations