© 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. 98242
    Prev
    Next
    INDEX
    Explanations

    free software or delivery

    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
    电视台
    -0.70
     lade
    -0.70
     blossomed
    -0.69
    Jegy
    -0.68
    纪念
    -0.68
    Phones
    -0.68
     Gouver
    -0.66
     太阳
    -0.66
     tắc
    -0.66
    ofu
    -0.66
    POSITIVE LOGITS
    ware
    1.06
    trial
    1.02
     trial
    1.02
     récents
    0.90
     UIApplication
    0.87
    bies
    0.84
    economics
    0.81
     forever
    0.81
    mium
    0.81
     version
    0.81
    Activations Density 0.064%

    No Known Activations