© 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. 191998
    Prev
    Next
    INDEX
    Explanations

    front edge

    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
     supernatural
    0.44
    SUBJECT
    0.40
     supersonic
    0.39
     supernat
    0.38
     supercritical
    0.38
     subjected
    0.38
     сверх
    0.38
    磔
    0.38
     unresponsive
    0.37
     Starr
    0.37
    POSITIVE LOGITS
     엔진
    0.50
     Engine
    0.48
     engine
    0.47
     фрон
    0.46
     delanter
    0.46
     front
    0.46
    前面的
    0.46
    前端
    0.45
     Front
    0.45
     Ahead
    0.44
    Activations Density 0.000%

    No Known Activations