© 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. 40-GEMMASCOPE-2-RES-262K
    7. 137657
    Prev
    Next
    INDEX
    Explanations

    david followed by surnames

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    一半
    0.46
    TextAlign
    0.44
    ராய
    0.41
     risol
    0.40
     τί
    0.40
    文件名
    0.40
     correlates
    0.39
    佺
    0.39
     Monter
    0.39
    璟
    0.38
    POSITIVE LOGITS
    ०
    0.50
    و
    0.47
    ව
    0.42
    will
    0.41
    mvc
    0.41
    nimmt
    0.39
     Depot
    0.39
    bromide
    0.39
    was
    0.38
    ो
    0.38
    Activations Density 0.001%

    No Known Activations