© 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. 568
    Prev
    Next
    INDEX
    Explanations

    numbers and colons

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

    programming code keywords

    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
    した
    0.94
    c
    0.68
     up
    0.67
    った
    0.64
    ก
    0.64
    あ
    0.62
    은
    0.62
    RO
    0.60
    AC
    0.60
    σ
    0.60
    POSITIVE LOGITS
    रित
    0.71
    <0xA0>
    0.65
    ؛
    0.63
    ،
    0.61
    <0x80>
    0.59
    <0x81>
    0.59
    ни
    0.59
     SERVICES
    0.58
    <0x94>
    0.57
    ")
    0.57
    Activations Density 0.000%

    No Known Activations