© 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. 83703
    Prev
    Next
    INDEX
    Explanations

    contextual descriptions and listings

    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
    jár
    -0.84
     vī
    -0.83
    Điện
    -0.82
    nī
    -0.81
    )()
    -0.80
     кухни
    -0.79
    acide
    -0.77
    лосо
    -0.75
     Antibody
    -0.74
     older
    -0.74
    POSITIVE LOGITS
     漫
    0.78
    それでは
    0.77
    avoir
    0.76
    uc
    0.74
     uds
    0.73
     saites
    0.73
     Waray
    0.72
    ĭ
    0.72
    อล
    0.72
     gan
    0.71
    Activations Density 0.010%

    No Known Activations