© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9858
    Prev
    Next
    INDEX
    Explanations

    tutorialspoint

    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
    ଳ
    1.35
     Engineering
    1.32
     allied
    1.27
     alliance
    1.27
     Albert
    1.26
     Observatory
    1.25
     Horticulture
    1.25
     Industry
    1.24
     PHY
    1.24
     engineering
    1.24
    POSITIVE LOGITS
    ያስ
    1.14
    赤ちゃん
    1.14
     gördüğünüz
    1.14
     posiad
    1.13
    てもら
    1.12
    降
    1.11
     bebê
    1.11
    躇
    1.10
    就很
    1.10
    ্বরের
    1.09
    Activations Density 0.059%

    No Known Activations