© 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. 113645
    Prev
    Next
    INDEX
    Explanations

    numbered lists, Roman numerals, and groups

    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
     on
    -2.00
    ,
    -1.98
     that
    -1.78
     with
    -1.78
     at
    -1.58
     of
    -1.47
    落ちて
    -1.41
     all
    -1.38
     նաև
    -1.38
     to
    -1.34
    POSITIVE LOGITS
    這個
    1.61
    ᵗ
    1.57
     because
    1.51
    这是
    1.51
    ↵↵
    1.49
    这次
    1.48
    $.
    1.42
    这个
    1.41
    这
    1.41
    ле
    1.40
    Activations Density 0.083%

    No Known Activations