© 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. 83734
    Prev
    Next
    INDEX
    Explanations

    inverted quotes

    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
     quoting
    -0.92
     quoted
    -0.80
     ATX
    -0.72
    死
    -0.72
     CITED
    -0.71
    verzeichnis
    -0.70
     เซ
    -0.70
    ("<
    -0.69
     condu
    -0.68
     malice
    -0.68
    POSITIVE LOGITS
     scare
    1.18
     single
    0.92
     frighten
    0.88
     scaring
    0.87
     scares
    0.85
    单
    0.81
    шеб
    0.80
    single
    0.77
    <'
    0.76
     inverted
    0.75
    Activations Density 0.040%

    No Known Activations