© 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. 34-GEMMASCOPE-RES-131K
    7. 31567
    Prev
    Next
    INDEX
    Explanations

    documentation and sources

    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_34/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
     การ์ตูน
    -0.91
    farbe
    -0.84
    になりますが
    -0.82
    ckeye
    -0.79
    鹟
    -0.78
     dels
    -0.78
    Signals
    -0.77
     poko
    -0.77
    Fordítás
    -0.77
    ᕱ
    -0.77
    POSITIVE LOGITS
     written
    4.00
     stated
    2.72
    written
    2.70
     wrote
    2.67
     написано
    2.56
     says
    2.55
    Written
    2.47
     Written
    2.47
     scritto
    2.45
     escrito
    2.27
    Activations Density 0.085%

    No Known Activations