© 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. 110887
    Prev
    Next
    INDEX
    Explanations

    Distributed under license

    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
     Lives
    -0.87
     visible
    -0.85
    oral
    -0.84
     puta
    -0.81
    ⩾
    -0.75
     dorado
    -0.73
     Visible
    -0.73
    %[
    -0.72
    mai
    -0.71
     poffible
    -0.71
    POSITIVE LOGITS
     ASSIGN
    0.93
    sumowanie
    0.92
    GridLayout
    0.90
     éduc
    0.83
    ghest
    0.82
    Francesca
    0.82
    排
    0.82
     kerjasama
    0.81
    getMinutes
    0.80
     irrational
    0.79
    Activations Density 0.005%

    No Known Activations