© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24525
    Prev
    Next
    INDEX
    Explanations

    membership inference

    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_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
    म
    0.53
    hosts
    0.51
    lh
    0.43
    ل
    0.42
    操作
    0.41
    Dat
    0.41
    eing
    0.40
    lash
    0.39
    MAN
    0.39
    Ve
    0.39
    POSITIVE LOGITS
     entitles
    0.49
     solv
    0.46
     dues
    0.46
     femminile
    0.45
     nupt
    0.45
     dissolution
    0.44
    )}^
    0.43
    )}^{
    0.42
     vertu
    0.42
     fluvial
    0.42
    Activations Density 0.010%

    No Known Activations