© 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. 90741
    Prev
    Next
    INDEX
    Explanations

    related album arrives breadcrumb integer

    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
    وفي
    -0.75
     zí
    -0.73
    Ⓘ
    -0.73
     numOf
    -0.73
     Wiss
    -0.72
    ruby
    -0.71
    coba
    -0.69
    Lista
    -0.69
     zabud
    -0.69
     Baek
    -0.68
    POSITIVE LOGITS
    Nottingham
    0.79
    landen
    0.71
    addon
    0.71
     settlements
    0.67
     Nottingham
    0.66
     decoded
    0.66
    Emil
    0.65
    edonian
    0.65
     YouTube
    0.65
     flea
    0.65
    Activations Density 0.048%

    No Known Activations