© 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. 40987
    Prev
    Next
    INDEX
    Explanations

    noun phrases or descriptive pairs

    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
    Max
    0.39
    วะ
    0.38
     Wink
    0.35
     sen
    0.35
     Max
    0.35
     bore
    0.35
     bullets
    0.35
    Dollar
    0.35
     wink
    0.34
    ε
    0.34
    POSITIVE LOGITS
    췄
    0.45
    sieh
    0.44
     unary
    0.43
     MERCHANT
    0.43
     Анастасия
    0.42
    ರ್ಚ
    0.41
    FileChooser
    0.41
    एसपी
    0.39
    ajada
    0.39
    ಿಸಿದ್ದರು
    0.39
    Activations Density 0.000%

    No Known Activations