© 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. 40-GEMMASCOPE-2-RES-65K
    7. 50298
    Prev
    Next
    INDEX
    Explanations

    display of X or display function

    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_40_width_65k_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
    *
    0.62
     disclosure
    0.50
    /
    0.48
    ld
    0.46
     into
    0.46
     disclosed
    0.46
    Ü
    0.46
    ='/
    0.46
     fail
    0.44
     Vene
    0.44
    POSITIVE LOGITS
    ಿರಿ
    0.50
     fuertes
    0.48
     කාල
    0.48
     automorphisms
    0.47
     mensagens
    0.47
    ные
    0.47
    jande
    0.46
    verhalten
    0.46
     publice
    0.45
    ગે
    0.45
    Activations Density 0.018%

    No Known Activations