© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13169
    Prev
    Next
    INDEX
    Explanations

    declaring software dependencies

    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
    Negative Logits
    Twig
    1.43
    yth
    1.37
    underland
    1.34
     revolving
    1.33
     interrelated
    1.33
    <bos>
    1.31
     fancy
    1.30
    ্ত্র
    1.26
    ங்கிணை
    1.26
     superf
    1.25
    POSITIVE LOGITS
     piatta
    1.68
     उसका
    1.58
    ="<?=
    1.58
     regole
    1.58
     Callable
    1.55
     сіль
    1.54
     Shekhar
    1.54
     ("
    1.54
    ılara
    1.53
    memberNameLink
    1.48
    Activations Density 0.000%

    No Known Activations