© 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. 10-GEMMASCOPE-RES-131K
    7. 41081
    Prev
    Next
    INDEX
    Explanations

    ir sequences

    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
    圌
    -2.94
     всех
    -2.91
     было
    -2.80
     был
    -2.63
     hermanas
    -2.61
     свою
    -2.58
    檍
    -2.56
     素人
    -2.47
    愎
    -2.44
     onCreateView
    -2.42
    POSITIVE LOGITS
    </i>
    3.38
    (
    3.22
     This
    2.81
     Their
    2.72
    The
    2.70
    銲
    2.67
    ";
    2.66
    [
    2.66
     Lately
    2.58
    逦
    2.58
    Activations Density 0.071%

    No Known Activations