© 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. 82516
    Prev
    Next
    INDEX
    Explanations

    articles published in

    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
     Lou
    -0.89
    U
    -0.87
     Erfolg
    -0.87
    tf
    -0.85
    Ric
    -0.85
     verstärkt
    -0.85
    >=
    -0.83
     U
    -0.82
     Lucas
    -0.82
    IVO
    -0.81
    POSITIVE LOGITS
     in
    2.47
     published
    1.73
     appearing
    1.57
     appeared
    1.51
    appearing
    1.50
    出现在
    1.38
     printed
    1.38
    appeared
    1.24
    published
    1.23
     publicada
    1.20
    Activations Density 0.068%

    No Known Activations