© 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. 65295
    Prev
    Next
    INDEX
    Explanations

    question headings and code structure

    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
    insley
    -0.80
    عى
    -0.76
    okay
    -0.76
     Krak
    -0.71
     spontan
    -0.71
     кап
    -0.70
    味の
    -0.70
    apuram
    -0.69
     داخلی
    -0.68
     spotlight
    -0.68
    POSITIVE LOGITS
     serving
    0.85
     FIC
    0.79
     Duluth
    0.78
     Serving
    0.75
     BQ
    0.72
    feature
    0.72
     fishing
    0.71
    uncio
    0.71
     Fishing
    0.70
    avari
    0.70
    Activations Density 0.011%

    No Known Activations