© 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
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6599
    Prev
    Next
    INDEX
    Explanations

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ();
    0.99
    ()+
    0.97
    ()+"
    0.97
    ()[
    0.96
     metody
    0.95
    ()">
    0.94
    ().
    0.94
    ()%
    0.93
     tangan
    0.92
    ('-',
    0.91
    POSITIVE LOGITS
    nested
    1.38
     watchlist
    1.35
     spoilers
    1.35
    motiv
    1.29
    inspiration
    1.29
    educ
    1.28
    alter
    1.28
     accession
    1.27
     reviewed
    1.25
     OBS
    1.25
    Activations Density 0.001%

    No Known Activations