© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100995
    Prev
    Next
    INDEX
    Explanations

    acronyms and word fragments

    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
    蕯
    -2.92
    
    -2.81
    ’
    -2.75
    寕
    -2.70
    喼
    -2.67
    0
    -2.63
    </em>
    -2.61
    嫱
    -2.55
    </sup>
    -2.53
    蒹
    -2.53
    POSITIVE LOGITS
    on
    2.86
    B
    2.64
    😦
    2.55
    蜴
    2.50
    ăzi
    2.50
    蹰
    2.48
    ":
    2.48
    The
    2.47
    」
    2.47
    F
    2.41
    Activations Density 0.028%

    No Known Activations