© 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. 50274
    Prev
    Next
    INDEX
    Explanations

    code elements and names

    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
     erw
    -0.83
    ੩
    -0.82
    ವಿ
    -0.80
     proved
    -0.76
    耘
    -0.76
     الأن
    -0.76
    ลด
    -0.75
     amplitudes
    -0.74
    towers
    -0.73
     Sere
    -0.72
    POSITIVE LOGITS
     هي
    0.89
    urlaub
    0.81
     Orville
    0.79
    kasten
    0.77
     あります
    0.77
     macOS
    0.75
    Panzer
    0.75
    oglio
    0.74
    agawa
    0.73
     quadrat
    0.73
    Activations Density 0.012%

    No Known Activations