© 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. 34-GEMMASCOPE-RES-131K
    7. 89789
    Prev
    Next
    INDEX
    Explanations

    trends in occurrences

    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_34/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
    istocene
    -1.05
    obrázek
    -1.05
                
    -1.02
    ی
    -0.98
    rrer
    -0.98
    屨
    -0.96
     producido
    -0.95
     gesuchten
    -0.95
    }
    -0.94
     wiederhol
    -0.93
    POSITIVE LOGITS
    setter
    1.66
    setters
    1.50
     trends
    1.38
    line
    1.37
    setting
    1.21
     Trend
    1.18
    趋势
    1.09
     toward
    1.07
     reversal
    1.07
    谞
    1.05
    Activations Density 0.009%

    No Known Activations