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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130373
    Prev
    Next
    INDEX
    Explanations

    scores with parentheses and hyphens

    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_22/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
     الأعمال
    -1.09
     এবং
    -1.07
     \
    -1.01
    不愿意
    -0.94
     న
    -0.94
    /+
    -0.92
    both
    -0.91
     --->
    -0.91
    心に
    -0.88
     ఈ
    -0.88
    POSITIVE LOGITS
     through
    1.08
     despite
    1.02
    zda
    0.99
     rağmen
    0.96
     gerçekten
    0.96
    providedIn
    0.95
    ₂)
    0.95
     without
    0.95
     slightly
    0.94
    zdo
    0.93
    Activations Density 0.002%

    No Known Activations