© 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. 31009
    Prev
    Next
    INDEX
    Explanations

    reproduce or explain models

    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
    ographies
    -0.78
    ungkin
    -0.77
     Gué
    -0.75
    Aktu
    -0.75
     coussin
    -0.74
     vaqueros
    -0.74
     Théâtre
    -0.73
    രി
    -0.72
     méthode
    -0.72
    ǣ
    -0.72
    POSITIVE LOGITS
     reproduce
    2.47
     reproducing
    2.45
     reproduces
    2.23
     reproduced
    1.98
     reproduction
    1.97
     Reproduce
    1.94
    Reproduction
    1.82
     Reproduction
    1.78
    Reprodu
    1.73
     reproducción
    1.59
    Activations Density 0.116%

    No Known Activations