© 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. 79170
    Prev
    Next
    INDEX
    Explanations

    words following specific terms

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

    delivered, confirm, everyone

    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
     Bolet
    0.48
     Support
    0.44
     Iterable
    0.44
     điều
    0.44
     बुखार
    0.43
     жидкости
    0.43
     Aj
    0.42
    લ
    0.42
     Moderate
    0.42
     Balls
    0.41
    POSITIVE LOGITS
    .//
    0.52
    accuracy
    0.49
    abortion
    0.49
    environ
    0.47
    initiated
    0.47
     বলতে
    0.46
    ynch
    0.46
    সিডেন্ট
    0.45
    Says
    0.45
    Harold
    0.45
    Activations Density 0.001%

    No Known Activations