© 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. 34624
    Prev
    Next
    INDEX
    Explanations

    reducing or preserving

    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
     Meksi
    -1.09
    yní
    -1.05
     ThreadPool
    -1.03
     NDEBUG
    -1.01
    itária
    -0.97
    forts
    -0.96
    theless
    -0.94
    نین
    -0.93
     facie
    -0.93
    Unary
    -0.92
    POSITIVE LOGITS
     vielleicht
    0.99
     não
    0.97
    razer
    0.96
    Except
    0.93
     warum
    0.91
     they
    0.88
     Is
    0.87
     where
    0.86
     heute
    0.86
     Explore
    0.85
    Activations Density 0.069%

    No Known Activations