© 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. 83898
    Prev
    Next
    INDEX
    Explanations

    lifting automobiles and Q&A

    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
     reed
    -0.71
    unitPattern
    -0.70
    சிய
    -0.70
     tuyến
    -0.70
     الأكثر
    -0.69
    iene
    -0.68
     Bure
    -0.67
    resign
    -0.66
     Corona
    -0.66
    paque
    -0.66
    POSITIVE LOGITS
     jack
    2.44
     jacks
    2.00
     lift
    1.98
     lifting
    1.92
    jack
    1.81
     lifts
    1.81
     Lift
    1.73
     Jack
    1.68
    Lift
    1.66
    Jack
    1.63
    Activations Density 0.022%

    No Known Activations