© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81361
    Prev
    Next
    INDEX
    Explanations

    starts with "while", "for", "leads"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VK
    0.47
    柑
    0.45
    idy
    0.44
     ម
    0.44
     sportsbook
    0.43
    ResultSet
    0.43
     battalion
    0.43
    bbi
    0.43
     vadanti
    0.42
    utebol
    0.41
    POSITIVE LOGITS
    ດ້
    0.45
     justicia
    0.44
     सेट
    0.43
     shared
    0.43
    گانی
    0.43
     geen
    0.42
     personas
    0.42
    اید
    0.42
    \|=
    0.42
     کوتاه
    0.42
    Activations Density 0.001%

    No Known Activations