© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64218
    Prev
    Next
    INDEX
    Explanations

    Paav Bhaaji

    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
     probablemente
    -1.06
    ERN
    -0.91
     продукции
    -0.90
    leigh
    -0.86
     правительства
    -0.85
     dispositivo
    -0.84
    पे
    -0.84
     товара
    -0.83
    skiej
    -0.83
     généralement
    -0.83
    POSITIVE LOGITS
     fiducia
    0.96
     versioni
    0.91
     colegios
    0.90
    hotels
    0.88
     žem
    0.88
     collectons
    0.88
     hoteles
    0.87
    #-
    0.86
     abstracta
    0.85
     stubs
    0.84
    Activations Density 0.028%

    No Known Activations