© 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. 74613
    Prev
    Next
    INDEX
    Explanations

    significant advantage

    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
     mighty
    0.51
    বলে
    0.47
     terrible
    0.46
     सत्तार
    0.45
     تقریباً
    0.45
    ින්
    0.44
     horrible
    0.44
     molar
    0.42
     ဖ
    0.42
     ойношот
    0.42
    POSITIVE LOGITS
    ut
    0.56
    eta
    0.54
    ividade
    0.54
    ol
    0.54
    en
    0.49
    olli
    0.48
    ia
    0.48
    as
    0.47
    ür
    0.47
    er
    0.45
    Activations Density 0.001%

    No Known Activations