© 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. 47878
    Prev
    Next
    INDEX
    Explanations

    Elisabeth 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_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
    1
    -3.77
    ,"
    -3.34
    …
    -3.11
    ]
    -2.92
    4
    -2.78
    (
    -2.59
     It
    -2.59
    ↵
    -2.58
    [
    -2.55
    </strong>
    -2.53
    POSITIVE LOGITS
    骓
    2.98
     ヶ
    2.95
    鶿
    2.88
    ⤴
    2.86
    zied
    2.78
    ⁉
    2.72
    歘
    2.72
     撮っ
    2.72
    錾
    2.70
     OGSÅ
    2.67
    Activations Density 0.013%

    No Known Activations