© 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. 89864
    Prev
    Next
    INDEX
    Explanations

    election contexts and code 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
    ACK
    -0.79
    Megan
    -0.75
    SCH
    -0.74
    ndor
    -0.73
     schedule
    -0.72
     Guardian
    -0.71
    uintptr
    -0.71
    кспер
    -0.71
    Urban
    -0.71
     friendly
    -0.71
    POSITIVE LOGITS
    oxo
    0.71
    长时间
    0.66
    ôtel
    0.66
     Arles
    0.63
     kulit
    0.62
     rubio
    0.61
     apabila
    0.60
    изнь
    0.60
     espac
    0.59
     achie
    0.58
    Activations Density 0.061%

    No Known Activations