© 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. 33503
    Prev
    Next
    INDEX
    Explanations

    Scott Rate, David Campos

    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
     Kun
    -0.90
     Probate
    -0.79
     Judicial
    -0.79
     хло
    -0.75
    <caption>
    -0.70
    CTA
    -0.70
     XSS
    -0.69
     gtk
    -0.69
     CTA
    -0.69
     GTP
    -0.69
    POSITIVE LOGITS
     Controller
    0.84
    ceno
    0.79
     городе
    0.73
     City
    0.73
    miu
    0.71
     Komunikasi
    0.70
     stigmati
    0.70
     arī
    0.70
     cilvē
    0.69
     Erle
    0.69
    Activations Density 0.006%

    No Known Activations