© 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. 22-GEMMASCOPE-RES-131K
    7. 71555
    Prev
    Next
    INDEX
    Explanations

    following Competition I No U 1 7

    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_22/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
     montr
    -1.25
     filtre
    -1.24
    iações
    -1.23
    ânsito
    -1.19
     suman
    -1.13
     nez
    -1.13
     aveug
    -1.13
    */
    -1.13
     तु
    -1.13
     rense
    -1.12
    POSITIVE LOGITS
     is
    1.05
    2
    1.02
    _
    1.00
    껍
    0.98
     äußer
    0.97
    al
    0.96
     успешно
    0.95
    true
    0.94
    各自
    0.94
     “
    0.91
    Activations Density 0.001%

    No Known Activations