© 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. 2195
    Prev
    Next
    INDEX
    Explanations

    Pag followed by et or ano

    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
    ected
    -0.79
    シュ
    -0.75
     src
    -0.70
    的发
    -0.70
     आहे
    -0.68
     twain
    -0.68
    メン
    -0.68
    营造
    -0.68
     Direktor
    -0.67
     Code
    -0.67
    POSITIVE LOGITS
     Pag
    1.05
     pag
    1.03
    Pag
    1.01
     PAG
    0.98
    дій
    0.92
    PAG
    0.83
    dsp
    0.81
     œil
    0.80
    นี
    0.79
     bedre
    0.78
    Activations Density 0.018%

    No Known Activations