© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3574
    Prev
    Next
    INDEX
    Explanations

    gun and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    UNION
    -0.78
    #--
    -0.76
    ings
    -0.75
    though
    -0.73
    戏剧
    -0.72
    ّر
    -0.71
    Скачать
    -0.70
    all
    -0.70
    Противо
    -0.69
     dunk
    -0.68
    POSITIVE LOGITS
     gun
    1.41
     Gun
    1.29
    Gun
    1.19
     guns
    1.18
     GUN
    1.17
    barrel
    1.16
    shots
    1.15
     barrel
    1.11
    nery
    1.08
    Guns
    1.07
    Activations Density 0.011%

    No Known Activations