© 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. 1907
    Prev
    Next
    INDEX
    Explanations

    `block` or section

    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
     scept
    1.58
    苷
    1.54
     conseguir
    1.53
     sceptical
    1.51
    ؐ
    1.48
    破解
    1.47
    ikiran
    1.46
     bilayer
    1.41
     entourage
    1.40
     arriver
    1.39
    POSITIVE LOGITS
     §§
    1.40
     subd
    1.38
    sections
    1.33
     Ariz
    1.30
     subchapter
    1.30
    mitz
    1.29
     §
    1.27
     subparagraph
    1.23
     inciso
    1.23
     Lamps
    1.22
    Activations Density 0.272%

    No Known Activations