© 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. 11989
    Prev
    Next
    INDEX
    Explanations

    serial number

    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
     ſta
    -1.63
    y
    -1.62
     flung
    -1.58
    geſ
    -1.55
    鼙
    -1.49
     heridas
    -1.48
     爱
    -1.45
    konos
    -1.45
     дори
    -1.44
     But
    -1.43
    POSITIVE LOGITS
    '
    2.19
    ‘
    1.55
    —”
    1.43
     cadre
    1.40
    </i>
    1.38
    ここまで
    1.37
    さんへ
    1.36
    ्ष
    1.36
    A
    1.34
    ゎ
    1.34
    Activations Density 0.018%

    No Known Activations