© 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-65K
    7. 56681
    Prev
    Next
    INDEX
    Explanations

    states & motivations

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     tubules
    0.47
    iqué
    0.46
    쿰
    0.46
     slugs
    0.44
     sulfides
    0.44
     composés
    0.43
     AsyncTask
    0.43
     melodies
    0.43
     lenses
    0.42
    худ
    0.42
    POSITIVE LOGITS
    ت
    0.61
    t
    0.55
    त
    0.50
    opp
    0.50
     dort
    0.50
    وب
    0.48
    т
    0.48
    country
    0.48
     Party
    0.47
     অপরিচিত
    0.47
    Activations Density 0.009%

    No Known Activations