© 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. 14650
    Prev
    Next
    INDEX
    Explanations

    Vietnamese and technical terms

    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
     prefer
    1.23
    <em>
    1.20
     Gospels
    1.19
     equidistant
    1.13
     gossip
    1.13
     mutually
    1.12
     gid
    1.11
     embell
    1.11
     hh
    1.11
     herbs
    1.10
    POSITIVE LOGITS
    सीबी
    1.67
    iendo
    1.53
    ার্টমেন্ট
    1.51
    Raquete
    1.47
    ेक्स
    1.45
    น
    1.43
    รวจ
    1.39
    سك
    1.39
    নাকে
    1.38
    ЛИ
    1.37
    Activations Density 0.000%

    No Known Activations