© 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. 7158
    Prev
    Next
    INDEX
    Explanations

    questions and specific phrases

    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
     gorą
    -0.81
     برگزار
    -0.80
    !(
    -0.79
    品種
    -0.77
    lecht
    -0.76
     consenti
    -0.75
     война
    -0.74
     години
    -0.74
     spotless
    -0.74
     Landschaft
    -0.73
    POSITIVE LOGITS
    algunos
    0.82
     MRS
    0.80
    错了
    0.78
    hombres
    0.77
     martyr
    0.75
     соло
    0.75
    स्य
    0.74
     Verv
    0.74
    memcpy
    0.71
     Ln
    0.71
    Activations Density 0.000%

    No Known Activations