© 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. 53-GEMMASCOPE-2-RES-65K
    7. 8632
    Prev
    Next
    INDEX
    Explanations

    PIR cereal certain

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

    metallic, motion, silk, baby, bacon, Sebastian, jasmine

    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_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    workouts
    0.42
    Dru
    0.40
     স্যার
    0.39
    懸
    0.38
    Ша
    0.37
    ামার
    0.37
     হি
    0.37
    稿
    0.37
    特朗普
    0.37
    फी
    0.36
    POSITIVE LOGITS
     cereal
    0.61
     Cere
    0.53
     cere
    0.43
     cereals
    0.41
    cere
    0.41
     certain
    0.39
    cP
    0.39
     destruct
    0.38
    ċ
    0.38
     poseen
    0.38
    Activations Density 0.000%

    No Known Activations