© 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. 123668
    Prev
    Next
    INDEX
    Explanations

    Guinness Book

    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
    -2.72
    2
    -2.64
    </h3>
    -2.48
    3
    -2.27
    \
    -2.20
    this
    -2.19
    ﮨ
    -2.14
     midway
    -2.09
     ."
    -1.99
    or
    -1.92
    POSITIVE LOGITS
    skirt
    2.16
     Guinness
    2.13
    芣
    2.00
     “
    1.98
    挲
    1.92
    𝐓
    1.84
     of
    1.84
    出了一
    1.83
     jardins
    1.80
    了一口
    1.79
    Activations Density 0.002%

    No Known Activations