© 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. 12603
    Prev
    Next
    INDEX
    Explanations

    palms facing

    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
     桌
    1.23
    쭈
    1.21
    enka
    1.19
    렇
    1.18
     pare
    1.18
    olve
    1.16
    酌
    1.15
    pload
    1.14
    حو
    1.13
    ombies
    1.13
    POSITIVE LOGITS
     పరిస్థి
    1.32
    ときの
    1.31
    美しい
    1.27
    ใน
    1.25
    Ĝ
    1.23
     Gambar
    1.23
     रखता
    1.23
     pertenecen
    1.22
    ときは
    1.22
    予測
    1.21
    Activations Density 0.000%

    No Known Activations