© 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. 16-GEMMASCOPE-2-RES-262K
    7. 145413
    Prev
    Next
    INDEX
    Explanations

    skillful play

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     caminar
    0.52
     trener
    0.52
     dirigir
    0.50
     soloist
    0.50
     savent
    0.49
    けると
    0.48
     jouer
    0.48
    щихся
    0.48
    贼
    0.46
     wonderland
    0.46
    POSITIVE LOGITS
    ون
    0.58
     shavings
    0.50
    ta
    0.50
    hand
    0.50
    tin
    0.50
    throat
    0.49
     inhalation
    0.49
    鍝
    0.49
     approvals
    0.48
     extremities
    0.47
    Activations Density 0.000%

    No Known Activations