© 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. 109033
    Prev
    Next
    INDEX
    Explanations

    toast and software licenses

    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
     dolar
    -0.84
    filterBy
    -0.73
     diapers
    -0.71
     mieten
    -0.71
    críbete
    -0.70
    higen
    -0.69
    Ehrungen
    -0.69
     kakak
    -0.69
     inverter
    -0.68
    グルメ
    -0.68
    POSITIVE LOGITS
     toast
    1.52
     Toast
    1.36
     toaster
    0.97
    Toast
    0.97
    showToast
    0.91
    🍞
    0.91
    toast
    0.88
     toasted
    0.85
     stanie
    0.81
    ொ
    0.81
    Activations Density 0.001%

    No Known Activations