Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8723
    Prev
    Next
    INDEX
    Explanations

    cabinet government roles

    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
     로
    -0.94
    heatmap
    -0.83
    jutan
    -0.78
     Produkten
    -0.78
    宽
    -0.77
    öten
    -0.76
     Which
    -0.74
    gernaut
    -0.74
    Kik
    -0.73
    ന്റെ
    -0.73
    POSITIVE LOGITS
     ministers
    1.23
     secretary
    1.11
     rank
    0.91
    ᑎ
    0.90
     Ministers
    0.90
    venes
    0.88
     hiburan
    0.87
    etry
    0.86
    SurfaceView
    0.84
     Secretaries
    0.83
    Activations Density 0.006%

    No Known Activations