© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11439
    Prev
    Next
    INDEX
    Explanations

    Vietnamese and Adobe Express

    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_7_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
    ernel
    2.18
    validators
    2.11
     osobe
    2.04
     آبی
    2.02
    æ
    2.01
    rail
    2.01
    ettek
    1.99
    keiten
    1.98
    feature
    1.98
    üyada
    1.98
    POSITIVE LOGITS
    ంద్ర
    2.61
    жала
    2.60
    র
    2.56
     Eastman
    2.51
    ྕ
    2.50
     Merle
    2.49
    Spoiler
    2.47
    🥸
    2.44
    ἲ
    2.44
    lent
    2.43
    Activations Density 0.005%

    No Known Activations