© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89799
    Prev
    Next
    INDEX
    Explanations

    links and URLs

    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
    แนว
    -0.93
    Inno
    -0.74
     mantis
    -0.71
     congre
    -0.69
     NARR
    -0.69
     Sankt
    -0.69
     Antigua
    -0.66
     facil
    -0.66
     kimchi
    -0.65
     smitten
    -0.65
    POSITIVE LOGITS
     Link
    3.64
    Link
    3.16
     link
    3.03
    link
    2.91
    LINK
    2.63
     LINK
    2.59
    リンク
    2.16
     Links
    1.98
     links
    1.82
     リンク
    1.80
    Activations Density 0.057%

    No Known Activations