© 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. 102416
    Prev
    Next
    INDEX
    Explanations

    speed or slowness

    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
    后来
    -1.20
     you
    -1.14
    чники
    -1.11
    焢
    -1.09
    綃
    -1.09
    unun
    -1.08
    꽁
    -1.07
    晳
    -1.05
    
    -1.05
    需要
    -1.05
    POSITIVE LOGITS
     to
    1.46
     môžete
    1.41
     môže
    1.37
     シャツ
    1.23
    Toluene
    1.20
     tých
    1.17
     Already
    1.16
    }$.
    1.16
    ambut
    1.16
    hejiang
    1.15
    Activations Density 0.024%

    No Known Activations