© 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. 118523
    Prev
    Next
    INDEX
    Explanations

    time stamps and includes

    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
     Probe
    -0.71
    噪
    -0.70
     LaTeX
    -0.70
    聪明
    -0.69
    あらすじ
    -0.67
    lawful
    -0.66
    luan
    -0.66
    millions
    -0.66
    ->{
    -0.66
     maisons
    -0.65
    POSITIVE LOGITS
     Mond
    0.71
     Entscheid
    0.71
    link
    0.70
     save
    0.70
     Hop
    0.69
    iol
    0.68
     Element
    0.68
     Hodgkin
    0.68
     hypot
    0.68
    libert
    0.66
    Activations Density 0.058%

    No Known Activations