© 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. 10-GEMMASCOPE-RES-131K
    7. 127493
    Prev
    Next
    INDEX
    Explanations

    names starting with De or Gra

    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_10/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
     inept
    -2.52
    ным
    -2.47
     predominant
    -2.42
    ли
    -2.41
    嚶
    -2.39
     treasured
    -2.38
     esteemed
    -2.36
    ta
    -2.30
     prized
    -2.27
     staunch
    -2.27
    POSITIVE LOGITS
    ↵
    2.34
     suena
    2.08
     officielles
    1.92
    芣
    1.91
     you
    1.91
     seguramente
    1.90
     instruções
    1.85
    鲥
    1.85
     Mayıs
    1.84
     efectivamente
    1.84
    Activations Density 0.055%

    No Known Activations