© 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. 185731
    Prev
    Next
    INDEX
    Explanations

    Kv, settings, or languages

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

    social context and personal situations

    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
    时间
    0.47
     étude
    0.46
     timeLeft
    0.44
     reigned
    0.43
    場合は
    0.43
    Morgan
    0.43
     destro
    0.43
    ೆ
    0.42
    élie
    0.42
     elapse
    0.42
    POSITIVE LOGITS
    numericUpDown
    0.55
    statusBar
    0.45
    itemBackground
    0.45
     बारे
    0.44
     ಸ್ನೇಹಿತ
    0.44
    دل
    0.44
    viendo
    0.44
    mä
    0.43
     menurut
    0.43
     UIBarButtonItem
    0.42
    Activations Density 0.001%

    No Known Activations