© 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. 517
    Prev
    Next
    INDEX
    Explanations

    places and their affiliations

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

    geopolitical entities

    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
    ம்
    0.51
    й
    0.50
    ويه
    0.49
     هڪ
    0.48
    <unused653>
    0.48
    ين
    0.48
     asistencia
    0.47
     bás
    0.46
     as
    0.46
     كه
    0.45
    POSITIVE LOGITS
    ۰
    0.50
    。
    0.48
    >
    0.48
    ار
    0.46
    -
    0.45
     attorney
    0.43
    र्फ
    0.41
    Nel
    0.40
    रम
    0.40
    Q
    0.40
    Activations Density 1.593%

    No Known Activations