© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85581
    Prev
    Next
    INDEX
    Explanations

    applying for loans or services

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     unsettling
    0.52
     inquiet
    0.51
    anner
    0.49
     பே
    0.47
     Hailey
    0.47
     Викто
    0.47
    र
    0.47
     Spaniards
    0.46
    '\
    0.46
    دا
    0.45
    POSITIVE LOGITS
     drink
    0.44
    ڑک
    0.43
     target
    0.42
     loca
    0.41
     beverage
    0.41
     border
    0.41
    <0x0D>
    0.40
     brake
    0.40
     extrac
    0.39
     wood
    0.38
    Activations Density 0.001%

    No Known Activations