© 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. 116651
    Prev
    Next
    INDEX
    Explanations

    ornamentation and decorative patterns

    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
     magne
    -0.86
     карти
    -0.80
    askan
    -0.79
    UMENTO
    -0.77
    äure
    -0.77
     substr
    -0.77
    ınca
    -0.77
    ⟦
    -0.77
    }}\
    -0.76
    торы
    -0.74
    POSITIVE LOGITS
     motifs
    1.52
     motif
    1.21
     запол
    1.15
     patterns
    1.15
     pattern
    1.06
     motyw
    0.98
     diaper
    0.96
     мотива
    0.96
     relleno
    0.96
     motivos
    0.95
    Activations Density 0.021%

    No Known Activations