© 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. 736
    Prev
    Next
    INDEX
    Explanations

    custom object properties

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

    DataFrame and coding libraries

    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
    Negative Logits
     is
    0.83
    _
    0.78
    ,
    0.70
    ')
    0.68
     =
    0.62
     बॉलीवुड
    0.61
    }=\
    0.59
     médicos
    0.59
     svenska
    0.59
    )
    0.58
    POSITIVE LOGITS
    ב
    1.13
    (
    1.04
    ه
    1.01
    and
    0.93
    it
    0.86
    न
    0.86
    د
    0.84
    ন
    0.84
    ال
    0.83
    at
    0.82
    Activations Density 0.004%

    No Known Activations