© 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. 11974
    Prev
    Next
    INDEX
    Explanations

    surname followed by initials

    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
     серпня
    1.44
     бо
    1.35
    <unused971>
    1.34
    toadd
    1.34
    <unused970>
    1.32
    setDisplay
    1.32
    .$;
    1.32
    اندار
    1.30
    <unused967>
    1.29
    <unused1957>
    1.29
    POSITIVE LOGITS
     silencio
    1.29
     telah
    1.08
    করণ
    1.05
     adalah
    1.03
     Emory
    1.02
     "
    1.00
     tiene
    0.94
     seja
    0.91
     forgot
    0.91
     masih
    0.90
    Activations Density 0.057%

    No Known Activations