© 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. 75502
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    犹豫
    -0.84
    setToolTip
    -0.80
    reiras
    -0.77
    ❕
    -0.75
    gerichts
    -0.75
     sats
    -0.73
    ключа
    -0.73
     везе
    -0.72
     representante
    -0.71
    êu
    -0.71
    POSITIVE LOGITS
    akad
    0.88
     read
    0.82
     reads
    0.82
    |}{
    0.80
     lok
    0.79
     избран
    0.78
     melh
    0.78
    在天
    0.77
     ਅ
    0.77
     music
    0.77
    Activations Density 0.005%

    No Known Activations