© 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. 91317
    Prev
    Next
    INDEX
    Explanations

    in followed by place names

    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
    when
    -1.15
    山形
    -1.10
    Nearly
    -1.04
    Almost
    -1.02
     ingrained
    -0.97
     sostanze
    -0.96
    ？』
    -0.93
    ☆☆
    -0.93
    Every
    -0.89
    rines
    -0.89
    POSITIVE LOGITS
     virš
    1.04
     réfléchir
    0.94
     tė
    0.91
     sprend
    0.89
    なのでしょう
    0.89
     opravdu
    0.87
     prosím
    0.87
     aukš
    0.85
     mieste
    0.85
     asmen
    0.85
    Activations Density 0.065%

    No Known Activations