© 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. 185045
    Prev
    Next
    INDEX
    Explanations

    distance, service, seams, deceased, tracks, price

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

    statement, restaurants, cow, tremor

    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
    や
    0.59
    5
    0.49
     of
    0.46
    等多
    0.44
    6
    0.43
     populous
    0.42
    1
    0.42
    0
    0.42
     is
    0.41
     rapide
    0.41
    POSITIVE LOGITS
     спраши
    0.61
     разговари
    0.50
     текст
    0.48
    ресенье
    0.48
     স্বীকার
    0.46
     bày
    0.46
     conversar
    0.46
     তাঁদের
    0.46
    ács
    0.45
     расска
    0.45
    Activations Density 0.001%

    No Known Activations