© 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. 80093
    Prev
    Next
    INDEX
    Explanations

    viewport width parameter

    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
     a
    0.47
     with
    0.42
     to
    0.41
     Head
    0.41
     BIS
    0.41
     u
    0.41
     City
    0.41
     Nome
    0.40
     about
    0.40
     ste
    0.40
    POSITIVE LOGITS
    ១
    0.52
    LinkedList
    0.50
    encerramento
    0.49
    𒁹
    0.47
    좔
    0.46
    㕫
    0.46
    ньше
    0.46
    apayati
    0.46
    autoprefixer
    0.45
    ヤモンド
    0.45
    Activations Density 0.000%

    No Known Activations