© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65866
    Prev
    Next
    INDEX
    Explanations

    case/project descriptions

    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
     ndani
    -0.77
    origen
    -0.77
     pavimento
    -0.73
    therin
    -0.71
    Ŵ
    -0.69
    heavy
    -0.69
    مثلة
    -0.69
     petitioner
    -0.69
    pekt
    -0.68
     православ
    -0.68
    POSITIVE LOGITS
    我们
    0.82
    rasi
    0.82
    মান
    0.80
     Sidebar
    0.80
    诗
    0.79
    我们在
    0.79
    我們
    0.79
    こん
    0.78
    estro
    0.77
    Ε
    0.77
    Activations Density 0.067%

    No Known Activations