© 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. 65752
    Prev
    Next
    INDEX
    Explanations

    A: Answer

    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
     in
    -1.62
     or
    -1.13
     Patrick
    -0.87
     In
    -0.87
     (
    -0.85
     of
    -0.85
     cases
    -0.85
     ((
    -0.84
     from
    -0.83
    вало
    -0.83
    POSITIVE LOGITS
    <blockquote>
    0.98
     widok
    0.97
     новую
    0.95
    鈥
    0.86
     travailler
    0.85
     vorgestellt
    0.85
     déplacer
    0.85
     recentemente
    0.85
     provoquer
    0.84
     élev
    0.84
    Activations Density 0.005%

    No Known Activations