© 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. 109008
    Prev
    Next
    INDEX
    Explanations

    pay per

    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
     soigne
    -0.76
     demonios
    -0.75
     المض
    -0.73
     maire
    -0.71
    ledem
    -0.70
     folie
    -0.69
    tedly
    -0.69
     Stedman
    -0.69
    гина
    -0.67
     bourgeo
    -0.67
    POSITIVE LOGITS
     pay
    4.31
     Pay
    3.47
    pay
    3.38
    Pay
    3.33
     PAY
    3.08
    PAY
    2.86
     PPV
    2.05
     Payne
    1.55
     pays
    1.52
     PPC
    1.38
    Activations Density 0.042%

    No Known Activations