© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 107263
    Prev
    Next
    INDEX
    Explanations

    destruction and park names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    o
    0.74
    as
    0.70
    old
    0.59
    وير
    0.58
    not
    0.57
    page
    0.55
    food
    0.55
    folg
    0.55
    fromi
    0.55
    chor
    0.54
    POSITIVE LOGITS
     BAFTA
    0.61
    מ
    0.61
    Ꮨ
    0.60
     Erie
    0.58
     convene
    0.56
    സ്
    0.55
     tych
    0.55
     allege
    0.55
     tekrar
    0.54
     LAKE
    0.54
    Activations Density 0.000%

    No Known Activations