© 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. 12795
    Prev
    Next
    INDEX
    Explanations

    Do you questions

    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
    Accueil
    1.39
    чная
    1.35
    ссер
    1.35
    """,
    1.33
    ઍ
    1.30
     //$
    1.30
    ઔ
    1.29
    icado
    1.27
    PAAm
    1.26
     terasa
    1.24
    POSITIVE LOGITS
    ০
    1.62
     произ
    1.50
    ०
    1.46
    ۰
    1.45
    a
    1.37
    orp
    1.36
    arikat
    1.31
    ००
    1.31
    opera
    1.31
    igham
    1.30
    Activations Density 0.000%

    No Known Activations