© 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. 115966
    Prev
    Next
    INDEX
    Explanations

    Choose or license

    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
     الأ
    -0.87
    Cordialement
    -0.86
    怎樣
    -0.82
     craters
    -0.82
    Anh
    -0.80
     ?
    -0.76
    之家
    -0.75
     있어
    -0.74
    がん
    -0.74
     VEGF
    -0.74
    POSITIVE LOGITS
     اپل
    0.93
    '>";
    0.82
    ೭
    0.81
    非常に
    0.80
     nastro
    0.80
     chod
    0.80
     longues
    0.78
    лары
    0.77
     шокола
    0.77
    ⢀
    0.76
    Activations Density 0.021%

    No Known Activations