© 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. 8526
    Prev
    Next
    INDEX
    Explanations

    social media handles and mentions

    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
     "";
    -1.59
     "";
    -1.49
    
    -1.39
    ;
    -1.38
    ANIEL
    -1.25
     האם
    -1.25
    心头
    -1.24
    ();
    -1.23
     mattino
    -1.23
     molest
    -1.22
    POSITIVE LOGITS
    volmente
    1.40
     we
    1.37
     have
    1.34
     khawatir
    1.33
     had
    1.31
     having
    1.31
    自分が
    1.28
    を行いました
    1.27
     levert
    1.27
    了一眼
    1.27
    Activations Density 0.054%

    No Known Activations