© 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. 75723
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     twenties
    -1.11
    ējās
    -1.00
    可选
    -0.99
    jā
    -0.97
     tercero
    -0.96
    生肖
    -0.96
    Responding
    -0.95
    Ѵ
    -0.94
     THERE
    -0.94
    mathrm
    -0.88
    POSITIVE LOGITS
     pourront
    0.96
    龊
    0.89
     
    0.87
     $\%$
    0.84
    tiness
    0.83
    糯
    0.82
    kone
    0.81
    Ǚ
    0.81
    ={}
    0.79
    로그
    0.79
    Activations Density 0.056%

    No Known Activations