© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 97985
    Prev
    Next
    INDEX
    Explanations

    generated Copyright

    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
     Daniele
    -0.76
     Unburied
    -0.69
     Incluso
    -0.68
    decl
    -0.66
     Polaris
    -0.66
     hollow
    -0.65
    orek
    -0.65
     ($.
    -0.65
    ined
    -0.64
     Souls
    -0.64
    POSITIVE LOGITS
    虐
    0.66
     sáb
    0.64
    tear
    0.63
    ШИ
    0.63
     לג
    0.62
    みる
    0.62
     trophies
    0.62
     Kola
    0.61
    мыш
    0.61
    ξη
    0.61
    Activations Density 0.066%

    No Known Activations