© 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. 7188
    Prev
    Next
    INDEX
    Explanations

    plotting and data visualization

    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
     xúc
    -0.81
    grouped
    -0.71
    状態で
    -0.71
     llamada
    -0.71
    theguardian
    -0.69
    ᱩ
    -0.69
     parlant
    -0.68
     planea
    -0.67
    polation
    -0.66
    かね
    -0.66
    POSITIVE LOGITS
     set
    1.32
    set
    1.13
    Chip
    0.93
    Set
    0.88
     azzurro
    0.81
    สา
    0.79
    matician
    0.77
     indigo
    0.76
    設定
    0.75
    设置
    0.75
    Activations Density 0.002%

    No Known Activations