© 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-65K
    7. 51578
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Keep"

    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_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
     вас
    0.51
     maintains
    0.50
    ４
    0.49
    اری
    0.46
    管理员
    0.46
     maintained
    0.46
    ٤
    0.45
     أبر
    0.44
     ensures
    0.44
     ૨
    0.44
    POSITIVE LOGITS
     faktor
    0.50
    on
    0.46
     fakt
    0.46
     hinsichtlich
    0.46
     on
    0.45
     quer
    0.45
    ogenesis
    0.44
    either
    0.44
    istin
    0.44
     vegg
    0.43
    Activations Density 0.019%

    No Known Activations