© 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. 93049
    Prev
    Next
    INDEX
    Explanations

    JavaScript code

    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
    蛱
    -1.53
    
    -1.37
     gewi
    -1.37
    liputi
    -1.33
     福袋
    -1.30
     மற்றும்
    -1.30
     إذا
    -1.30
     estadounid
    -1.28
     GameManager
    -1.28
     และ
    -1.27
    POSITIVE LOGITS
    </strong>
    1.45
     when
    1.37
     -
    1.33
    s
    1.33
    </b>
    1.32
     create
    1.27
     控
    1.27
          
    1.25
     contribute
    1.23
    1.23
    Activations Density 0.003%

    No Known Activations