© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108972
    Prev
    Next
    INDEX
    Explanations

    Seneca Lake

    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
     Ab
    -0.81
     Trees
    -0.74
     Input
    -0.74
    震
    -0.72
     Create
    -0.70
     assessed
    -0.70
    اشتی
    -0.68
     then
    -0.68
    Connectivity
    -0.68
    Input
    -0.68
    POSITIVE LOGITS
     Seneca
    0.91
    číta
    0.90
     Estable
    0.84
    Geneva
    0.83
    Lakes
    0.81
     linker
    0.79
    žen
    0.79
     Lodi
    0.77
     richieste
    0.77
     Geneva
    0.76
    Activations Density 0.022%

    No Known Activations