© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 250746
    Prev
    Next
    INDEX
    Explanations

    print

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     Collision
    0.46
     Thereby
    0.44
     Palis
    0.43
    🫂
    0.43
     Coll
    0.43
     singles
    0.43
     Collie
    0.43
    ীয়
    0.42
    atoria
    0.41
     quadrant
    0.41
    POSITIVE LOGITS
    大量
    0.48
     উদ্ধার
    0.48
     (!)
    0.45
     крупных
    0.45
     огромное
    0.44
     evaporated
    0.43
    lerinde
    0.43
     планы
    0.43
    慢
    0.43
    maq
    0.42
    Activations Density 0.000%

    No Known Activations