© 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. 82761
    Prev
    Next
    INDEX
    Explanations

    Google Chrome, Oxford Instruments

    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
    oxane
    -0.82
    лена
    -0.81
     windows
    -0.81
    ₡
    -0.81
     verdienen
    -0.81
    ု
    -0.79
    ℗
    -0.79
     familien
    -0.79
     Hudson
    -0.78
     Milán
    -0.78
    POSITIVE LOGITS
     mingling
    0.83
     vorüber
    0.80
    psic
    0.76
    っとり
    0.76
     intriguing
    0.75
    Sce
    0.75
     chúc
    0.75
    ougou
    0.74
     생각
    0.74
     menacing
    0.74
    Activations Density 0.000%

    No Known Activations