© 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. 60566
    Prev
    Next
    INDEX
    Explanations

    return to

    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
    jemahan
    -0.88
     gravedad
    -0.84
    Recept
    -0.82
    Пока
    -0.78
    ımda
    -0.77
    畢業
    -0.77
    Enciclopedia
    -0.77
    陲
    -0.75
    ництва
    -0.75
    ión
    -0.74
    POSITIVE LOGITS
     to
    1.94
     về
    1.17
     into
    1.10
     back
    1.09
     whence
    1.09
     towards
    1.00
     към
    0.91
     원
    0.90
     basics
    0.84
     toward
    0.83
    Activations Density 0.023%

    No Known Activations