© 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. 1089
    Prev
    Next
    INDEX
    Explanations

    compounds multiplicatively, sequentially

    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
     characterizes
    0.38
     cinqui
    0.38
    gypt
    0.37
    known
    0.37
     housings
    0.36
     определяет
    0.36
     whence
    0.36
     Nxa
    0.35
    岌
    0.35
     worldview
    0.35
    POSITIVE LOGITS
    љу
    0.41
    LAUNCH
    0.41
     रकम
    0.40
     transferred
    0.39
     रक्कम
    0.39
     relaunch
    0.39
     transferência
    0.38
    されない
    0.37
     reinstated
    0.37
     multiplicação
    0.36
    Activations Density 0.001%

    No Known Activations