© 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. 9073
    Prev
    Next
    INDEX
    Explanations

    check a

    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
    feed
    0.48
    feeds
    0.48
    리를
    0.43
    리로
    0.43
    క్సి
    0.42
    ⍵
    0.41
     Denny
    0.41
    готовка
    0.41
     Eton
    0.41
    ències
    0.41
    POSITIVE LOGITS
     লইয়
    0.50
     জেড
    0.45
    त्ति
    0.44
     kaleidoscopic
    0.44
     динами
    0.43
    IRM
    0.43
    ت
    0.43
     glossary
    0.43
    CHICAGO
    0.42
     মহল
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.