© 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. 116910
    Prev
    Next
    INDEX
    Explanations

    more, source, read

    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
     hiszen
    -0.96
    אַ
    -0.93
    ():
    -0.91
     mivel
    -0.90
    äsent
    -0.89
    Ț
    -0.87
     tragé
    -0.87
    ÍN
    -0.86
     armé
    -0.86
    entlich
    -0.86
    POSITIVE LOGITS
    truncated
    1.02
    trt
    0.95
     expresa
    0.95
     mohou
    0.94
    क़
    0.93
     sólida
    0.92
     downgraded
    0.90
     chercher
    0.89
     umož
    0.89
    したが
    0.88
    Activations Density 0.062%

    No Known Activations