© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38528
    Prev
    Next
    INDEX
    Explanations

    bullets and shots

    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
    Not in Any Lists

    No Comments

    Negative Logits
     بندی
    -0.79
    Poster
    -0.76
     Foto
    -0.73
    uč
    -0.72
    brushes
    -0.72
    hā
    -0.72
    nty
    -0.70
     WEDNESDAY
    -0.70
     orderId
    -0.69
    pinch
    -0.69
    POSITIVE LOGITS
     bullets
    4.41
     bullet
    4.22
    bullet
    3.13
     Bullets
    3.00
    bullets
    3.00
    Bullet
    2.80
     Bullet
    2.80
    Bullets
    2.78
     projectiles
    2.50
     projectile
    2.41
    Activations Density 0.049%

    No Known Activations