© 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. 16-GEMMASCOPE-2-RES-262K
    7. 145540
    Prev
    Next
    INDEX
    Explanations

    phone home, Blue berries, formulas, Generation, games, начал

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     format
    0.44
    る
    0.44
     age
    0.43
     nive
    0.43
     olt
    0.42
     anual
    0.41
     of
    0.40
    来自
    0.40
     ECD
    0.39
     EXEC
    0.39
    POSITIVE LOGITS
    odigd
    0.47
    aszt
    0.47
    でに
    0.46
     gesund
    0.46
    कोष्ठ
    0.45
     ಉತ್ಪನ್ನ
    0.44
    ኪ
    0.44
     namelijk
    0.44
    缽
    0.44
     _|
    0.44
    Activations Density 0.000%

    No Known Activations