© 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. 80728
    Prev
    Next
    INDEX
    Explanations

    phrases connecting clauses or lists

    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
     trilogy
    0.47
     stile
    0.45
     felicit
    0.44
    uig
    0.43
    ologico
    0.42
    in
    0.41
     blogs
    0.41
    inase
    0.41
     flores
    0.40
     ૩
    0.40
    POSITIVE LOGITS
    یک
    0.54
    фра
    0.53
    fou
    0.51
    pairwise
    0.50
    स्मै
    0.50
    ्ले
    0.49
    candidate
    0.48
    첫
    0.48
    次の
    0.47
    ैक
    0.46
    Activations Density 0.000%

    No Known Activations