© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128843
    Prev
    Next
    INDEX
    Explanations

    service experts centers

    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
    paravant
    -0.93
    🥚
    -0.93
     ڈ
    -0.89
    poem
    -0.89
     matematika
    -0.88
     ?',
    -0.87
    UIM
    -0.86
    みつ
    -0.85
    เปลี่ยน
    -0.85
    」,
    -0.85
    POSITIVE LOGITS
    了一句
    1.03
     you
    1.02
     fashionable
    0.98
    miyor
    0.97
    НЫ
    0.87
    gusted
    0.87
    Literat
    0.87
    There
    0.87
    Give
    0.86
     Believe
    0.85
    Activations Density 0.006%

    No Known Activations