© 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. 220576
    Prev
    Next
    INDEX
    Explanations

    non-english characters, names

    np_acts-logits-general · gemini-2.5-flash-lite

    extract decompose areas

    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
    fov
    0.49
    chainId
    0.46
    爍
    0.46
     kredit
    0.45
     ಸ್ನೇಹಿತ
    0.45
    Otp
    0.45
    সাইন
    0.45
    applied
    0.44
    oside
    0.44
     Kredit
    0.44
    POSITIVE LOGITS
    م
    0.51
     teenage
    0.45
     Ше
    0.45
    简单
    0.44
    出来
    0.44
     Farah
    0.44
     работой
    0.44
     из
    0.43
    ત
    0.43
    ال
    0.43
    Activations Density 0.000%

    No Known Activations