© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102904
    Prev
    Next
    INDEX
    Explanations

    special characters and operators

    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
     Baillargeon
    -0.82
     ontwikkeling
    -0.82
     conclusione
    -0.79
    楸
    -0.79
    }
    
    
    -0.77
     жк
    -0.77
    versite
    -0.77
    !!</
    -0.76
    ᚦ
    -0.76
     piattaforma
    -0.75
    POSITIVE LOGITS
     ()
    1.82
    ()
    1.61
     []
    1.55
    (),
    1.30
     -,
    1.23
     {}
    1.20
     !=
    1.19
     ×
    1.15
    []
    1.13
     (),
    1.13
    Activations Density 0.123%

    No Known Activations