© 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. 211474
    Prev
    Next
    INDEX
    Explanations

    happy baby

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

    dangerous outcomes and harm

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ndarray
    0.43
    स
    0.42
    ới
    0.39
    ವರೆಗೆ
    0.39
    ق
    0.39
    dimg
    0.38
    ತೆ
    0.38
     নেওয়া
    0.38
    c
    0.38
    Õ
    0.38
    POSITIVE LOGITS
     acquire
    0.56
     analyzer
    0.54
     Checker
    0.52
     Emulator
    0.52
     complementar
    0.50
     Hiz
    0.50
    ྛ
    0.49
     Hiro
    0.49
     Analyzer
    0.49
     Saver
    0.49
    Activations Density 0.004%

    No Known Activations