© 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. 13367
    Prev
    Next
    INDEX
    Explanations

    For example

    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
    ·
    1.15
     све
    1.04
     &
    1.02
    an
    1.01
     *
    0.99
     ·
    0.95
    is
    0.93
    독
    0.87
    ё
    0.84
     "
    0.84
    POSITIVE LOGITS
     correctAnswer
    1.98
    <unused1390>
    1.96
    ধানা
    1.95
     searchQuery
    1.94
    <unused949>
    1.93
    <unused872>
    1.92
    Bump
    1.89
    Mapped
    1.87
    सर्गिक
    1.87
    㥉
    1.86
    Activations Density 0.186%

    No Known Activations