© 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. 36720
    Prev
    Next
    INDEX
    Explanations

    input features

    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
     Gál
    0.39
    Theme
    0.39
     விஜய்
    0.38
    Michele
    0.37
    ıma
    0.37
    Vern
    0.37
    ईद
    0.37
     커
    0.36
    ినా
    0.36
    ⛏
    0.36
    POSITIVE LOGITS
     features
    0.97
    features
    0.93
     Features
    0.91
    Features
    0.86
     FEATURES
    0.78
     feature
    0.76
    FEATURES
    0.70
     Feature
    0.68
    feature
    0.67
     matrices
    0.64
    Activations Density 0.022%

    No Known Activations