© 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. 205712
    Prev
    Next
    INDEX
    Explanations

    options or directions

    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
     đón
    0.46
    ohnt
    0.46
    ၢ
    0.46
     giudice
    0.46
    Theater
    0.46
     murah
    0.46
     सस्ते
    0.46
     står
    0.45
     gevallen
    0.45
     sakura
    0.45
    POSITIVE LOGITS
     or
    0.49
     अथवा
    0.45
    的选择
    0.45
    各有
    0.43
    个
    0.42
    ى
    0.41
     individually
    0.41
    ediat
    0.39
     SQLite
    0.38
    もしくは
    0.38
    Activations Density 0.008%

    No Known Activations