© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 11289
    Prev
    Next
    INDEX
    Explanations

    examples and suggestions

    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
    ,
    2.64
    .
    2.49
     for
    2.28
     with
    2.27
     and
    2.23
     in
    2.20
     on
    2.11
    ;
    2.05
     from
    2.02
     by
    1.98
    POSITIVE LOGITS
     zwró
    2.34
     filóso
    2.32
    ከና
    2.20
    𒄷
    2.18
     kişinin
    2.18
     posiada
    2.18
     działa
    2.18
     liczba
    2.18
     kaliteli
    2.17
    kében
    2.15
    Activations Density 0.000%

    No Known Activations