© 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. 53-GEMMASCOPE-2-RES-262K
    7. 13873
    Prev
    Next
    INDEX
    Explanations

    engine displacement and type

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     unab
    0.40
    对待
    0.40
     केमिक
    0.39
     Hebrews
    0.39
    UIColor
    0.38
    できない
    0.38
    弐
    0.38
     Somalia
    0.37
    句子
    0.37
    QRSTUVWXYZ
    0.37
    POSITIVE LOGITS
     turbocharged
    1.01
     inline
    0.88
     turbo
    0.82
     Inline
    0.82
     V
    0.80
     engines
    0.78
    发动机
    0.78
     engine
    0.77
     powerplant
    0.77
    inline
    0.77
    Activations Density 0.020%

    No Known Activations