© 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. 4808
    Prev
    Next
    INDEX
    Explanations

    preventing errors

    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
     this
    0.95
     judicious
    0.90
     بذلك
    0.89
    arev
    0.85
    ः
    0.84
     excellent
    0.82
    anmoins
    0.82
    cez
    0.79
    this
    0.77
     व्यापक
    0.76
    POSITIVE LOGITS
    INotification
    1.42
    ]|[
    1.34
    뷊
    1.33
     '".$
    1.29
     不需要
    1.28
    投票
    1.28
    UTONIUM
    1.28
     开发
    1.25
    ﺧ
    1.25
     müsste
    1.25
    Activations Density 0.107%

    No Known Activations