© 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. 16-GEMMASCOPE-2-RES-16K
    7. 562
    Prev
    Next
    INDEX
    Explanations

    modifiers

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

    automated virtual silent

    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_16_width_16k_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
     of
    1.13
    ใน
    1.05
    在
    1.01
    お
    0.98
    ال
    0.93
    り
    0.93
    ಮ
    0.93
     của
    0.88
    ของ
    0.86
    માં
    0.86
    POSITIVE LOGITS
    ine
    0.78
    )
    0.77
    res
    0.75
    at
    0.75
    pe
    0.73
    ET
    0.73
    ิ
    0.72
    AH
    0.71
    us
    0.68
    IN
    0.68
    Activations Density 4.902%

    No Known Activations