© 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. 85262
    Prev
    Next
    INDEX
    Explanations

    programming syntax and scientific names

    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
    鲀
    -2.53
    </h4>
    -2.45
    烱
    -2.38
     */
    -2.28
    ↵↵
    -2.25
    
    -2.23
    0
    -2.19
    _{
    -2.17
     \\
    -2.03
     \
    -2.00
    POSITIVE LOGITS
    of
    3.16
     ヶ
    2.23
    {
    2.17
    褔
    2.11
     –
    2.11
    饪
    2.11
    い
    2.09
     „
    2.05
    r
    2.00
     în
    1.99
    Activations Density 0.000%

    No Known Activations