© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1840
    Prev
    Next
    INDEX
    Explanations

    mod rewrite gui cgi icon

    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
    izarre
    -0.93
     đeo
    -0.83
    läge
    -0.80
     pozycji
    -0.80
     націона
    -0.79
    SnackBar
    -0.79
    ῇ
    -0.79
    enovo
    -0.78
     herre
    -0.78
    Webpack
    -0.77
    POSITIVE LOGITS
     extra
    0.84
     natürlich
    0.83
    Să
    0.82
      
    0.81
     اضاف
    0.81
    Encontra
    0.80
     Fillmore
    0.79
     Essentials
    0.78
    yní
    0.77
    zug
    0.75
    Activations Density 0.064%

    No Known Activations