© 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. 130052
    Prev
    Next
    INDEX
    Explanations

    clover, sweetheart, brisket, Whitman

    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
    on
    -3.14
     
    -3.00
    izing
    -2.83
     erns
    -2.70
    e
    -2.67
    is
    -2.66
    would
    -2.53
     praktisch
    -2.52
     wilden
    -2.50
    t
    -2.50
    POSITIVE LOGITS
    凊
    2.80
    鉝
    2.56
    珰
    2.52
    雠
    2.52
    尛
    2.50
     admired
    2.50
    砹
    2.48
    怍
    2.48
     ignoring
    2.41
    葙
    2.38
    Activations Density 0.004%

    No Known Activations