© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    areas of

    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
    ysacchar
    -2.42
    
    -2.31
     Now
    -2.28
     It
    -2.16
     また
    -2.16
    ಞ
    -2.09
     While
    -2.09
     Organizador
    -2.02
    讴
    -2.02
    藹
    -2.00
    POSITIVE LOGITS
     of
    2.28
        
    2.17
     проблемы
    2.05
    </strong>
    2.05
     ſever
    1.91
    r
    1.91
     ‚
    1.90
     então
    1.88
     tetapi
    1.87
    皤
    1.86
    Activations Density 0.022%

    No Known Activations