© 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. 50969
    Prev
    Next
    INDEX
    Explanations

    history of

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

    prompts and intents

    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
    il
    0.59
    SHIFT
    0.50
    ai
    0.46
     shortage
    0.46
    z
    0.45
    ua
    0.45
    MARK
    0.45
    piel
    0.45
    Diploma
    0.45
     Connectivity
    0.45
    POSITIVE LOGITS
    엽
    0.49
     بیټ
    0.48
    經典
    0.48
    ოთ
    0.48
     کاسینو
    0.46
     asem
    0.46
    وريا
    0.44
     أغسطس
    0.43
    辦
    0.43
    Њ
    0.43
    Activations Density 0.000%

    No Known Activations