© 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-262K
    7. 11518
    Prev
    Next
    INDEX
    Explanations

    all rolled into one

    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
     aand
    0.50
     ו
    0.49
     và
    0.47
     และ
    0.47
     και
    0.45
     and
    0.44
     и
    0.44
     și
    0.43
     AND
    0.42
    Md
    0.42
    POSITIVE LOGITS
     одновременно
    0.48
    combined
    0.46
     zároveň
    0.45
     zugleich
    0.45
    ตลอด
    0.44
     동시에
    0.43
     simultaneously
    0.43
     existed
    0.42
    扰
    0.42
     superimposed
    0.41
    Activations Density 0.000%

    No Known Activations