© 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. 192219
    Prev
    Next
    INDEX
    Explanations

    flash and buildings

    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
    Fixed
    0.43
    琭
    0.42
    CHARGE
    0.42
    segu
    0.41
    scriptions
    0.40
    RELATED
    0.39
    defaults
    0.39
    fixed
    0.39
     misa
    0.39
    RECE
    0.38
    POSITIVE LOGITS
    ņ
    0.40
    toCharArray
    0.38
    racellular
    0.37
     svol
    0.37
     persp
    0.37
     svolge
    0.37
     lyophil
    0.37
    UnitTest
    0.37
    ņu
    0.37
     Conch
    0.36
    Activations Density 0.000%

    No Known Activations