© 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. 13022
    Prev
    Next
    INDEX
    Explanations

    specific details or goals

    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
    Negative Logits
    asses
    0.38
    仨
    0.38
    兩種
    0.37
     fathom
    0.37
    eight
    0.37
    𝐞
    0.37
     centaines
    0.36
     billions
    0.36
     blanche
    0.36
     dowol
    0.36
    POSITIVE LOGITS
     ____
    1.30
     _______
    1.26
     ______
    1.23
     ________
    1.23
     _____
    1.23
     [
    1.19
     __________
    1.18
    ____
    1.08
     xxx
    1.06
     ____________
    1.06
    Activations Density 0.089%

    No Known Activations