© 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. 31-GEMMASCOPE-2-RES-262K
    7. 205664
    Prev
    Next
    INDEX
    Explanations

    Python script

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     etched
    0.43
    Zhang
    0.43
     inciso
    0.43
     установлен
    0.42
    我在
    0.42
     nodos
    0.41
    IED
    0.41
     Hez
    0.40
    Conv
    0.40
    릅
    0.39
    POSITIVE LOGITS
     اختیار
    0.43
     आसानी
    0.42
    ans
    0.41
     من
    0.40
     Bolivia
    0.40
    an
    0.40
    gen
    0.39
     gratuitamente
    0.38
    one
    0.38
     आर्
    0.38
    Activations Density 0.003%

    No Known Activations