© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13033
    Prev
    Next
    INDEX
    Explanations

    french and spanish negation

    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
     le
    2.73
    ণ্য
    2.54
    انیہ
    2.27
    烷
    2.18
    球
    2.12
     ak
    2.11
    mo
    2.11
     '[
    2.04
    лектро
    2.02
    കാശ
    2.01
    POSITIVE LOGITS
     defaultstate
    2.77
    AnimationFrame
    2.74
    ᄐ
    2.72
    ệt
    2.68
    esquerda
    2.66
    dì
    2.61
    𝑵
    2.57
    Ons
    2.52
    getPlayer
    2.52
    ーストラ
    2.50
    Activations Density 0.002%

    No Known Activations