© 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. 10-GEMMASCOPE-RES-131K
    7. 1808
    Prev
    Next
    INDEX
    Explanations

    out of

    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_10/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
    </i>
    -2.11
    aided
    -1.91
     It
    -1.88
     jednocześnie
    -1.77
    儼
    -1.76
    美国的
    -1.75
    誒
    -1.74
    assemblée
    -1.73
    よろしくお願い
    -1.73
    外国
    -1.73
    POSITIVE LOGITS
     for
    1.95
    珝
    1.94
    авто
    1.80
    ECTOS
    1.78
     Wilayah
    1.77
     sosok
    1.76
     of
    1.75
    嫪
    1.72
    Bromoform
    1.70
    、
    1.69
    Activations Density 0.012%

    No Known Activations