© 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. 41-GEMMASCOPE-2-RES-262K
    7. 30007
    Prev
    Next
    INDEX
    Explanations

    driving vehicles

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     walking
    0.60
     walked
    0.50
     caminar
    0.49
    walking
    0.48
     walk
    0.47
     Walking
    0.46
    เดิน
    0.45
     Walks
    0.45
     walks
    0.44
    歩
    0.43
    POSITIVE LOGITS
     सावधानी
    0.45
     simulator
    0.43
    home
    0.41
     काळजी
    0.40
    🚗
    0.40
     Simulator
    0.40
    orph
    0.39
    simulator
    0.39
     azide
    0.39
     ascetic
    0.38
    Activations Density 0.001%

    No Known Activations