© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11247
    Prev
    Next
    INDEX
    Explanations

    replace file path placeholders

    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
    𝙖
    2.43
    一个
    2.32
    as
    2.25
    is
    2.24
    𝙧
    2.24
    asie
    2.22
    ingin
    2.11
    ו
    2.05
    a
    2.04
    an
    1.98
    POSITIVE LOGITS
     principales
    2.19
    OURCES
    1.99
    Ẻ
    1.99
    য়ের
    1.99
     Erste
    1.97
    اً
    1.95
     swoich
    1.95
    ことが
    1.93
    น์
    1.90
    Weitere
    1.90
    Activations Density 0.024%

    No Known Activations