© 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. 7068
    Prev
    Next
    INDEX
    Explanations

    pronouns and specific entities

    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
    すごく
    -1.02
    Depends
    -0.91
    めっちゃ
    -0.90
    depends
    -0.89
    pecially
    -0.85
    
    -0.85
     neri
    -0.84
    めちゃくちゃ
    -0.84
    Сам
    -0.83
     prochain
    -0.83
    POSITIVE LOGITS
     is
    1.23
     may
    1.16
     has
    0.92
     will
    0.86
     cannot
    0.85
     does
    0.78
    Abitanti
    0.77
     necess
    0.76
     would
    0.75
     não
    0.75
    Activations Density 0.006%

    No Known Activations