© 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. 10-GEMMASCOPE-RES-131K
    7. 59316
    Prev
    Next
    INDEX
    Explanations

    association for

    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_10/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
    黥
    -1.95
    '
    -1.95
    もちろん
    -1.87
     vêtements
    -1.84
    หรือ
    -1.84
    很赞
    -1.81
    饜
    -1.80
    快要
    -1.78
     seventy
    -1.74
    蓐
    -1.74
    POSITIVE LOGITS
     You
    2.27
     to
    2.14
     How
    1.71
     So
    1.63
     hovor
    1.56
     This
    1.55
    られた
    1.51
    }}{\
    1.49
     Just
    1.47
     And
    1.46
    Activations Density 0.036%

    No Known Activations