© 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. 34762
    Prev
    Next
    INDEX
    Explanations

    you followed by don't

    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
     isn
    -2.98
     wasn
    -2.91
     aren
    -2.56
     weren
    -2.47
     wouldn
    -2.36
     Wasn
    -2.30
     Didn
    -2.17
     cannot
    -2.16
     Doesn
    -2.14
     Wouldn
    -2.14
    POSITIVE LOGITS
     طويلة
    0.85
    
    0.83
     جميلة
    0.82
    ıldız
    0.81
     "`
    0.80
    aral
    0.80
    hto
    0.79
    colore
    0.77
    marck
    0.76
    кисло
    0.75
    Activations Density 0.056%

    No Known Activations