© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1525
    Prev
    Next
    INDEX
    Explanations

    I were or I had

    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_17_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
    %);
    0.98
     Prefer
    0.94
     ఇప్పటికే
    0.93
     either
    0.93
     دارای
    0.92
     ';
    0.92
     مناسب
    0.91
    已
    0.91
    已有
    0.90
    ?;
    0.90
    POSITIVE LOGITS
     fossero
    1.54
    were
    1.42
     WERE
    1.41
     fueran
    1.41
     weren
    1.39
    Were
    1.33
     hadn
    1.32
     were
    1.31
     Were
    1.22
     tivesse
    1.21
    Activations Density 0.315%

    No Known Activations