© 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. 4374
    Prev
    Next
    INDEX
    Explanations

    numbers and dimensions

    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
    ástica
    -0.79
    ásticas
    -0.77
    anyo
    -0.72
     actively
    -0.70
     Tans
    -0.68
     yank
    -0.67
     even
    -0.67
     Tufts
    -0.66
    adeloupe
    -0.66
     taught
    -0.66
    POSITIVE LOGITS
    announced
    0.80
     その他
    0.80
     habe
    0.79
     diameter
    0.79
     WANTED
    0.77
    总之
    0.77
     درو
    0.76
     gate
    0.76
     FIF
    0.76
    скольку
    0.75
    Activations Density 0.008%

    No Known Activations