© 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. 2821
    Prev
    Next
    INDEX
    Explanations

    reproduce or quote

    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
     circulation
    -1.30
     Circulation
    -1.27
     descriptions
    -1.02
    Circ
    -0.94
    circulation
    -0.93
    あくまで
    -0.83
     Circ
    -0.83
     описа
    -0.80
     DVDs
    -0.80
     순
    -0.77
    POSITIVE LOGITS
     reproduced
    3.73
     reproduce
    3.16
     quoted
    3.00
     reproduction
    2.59
     reproduces
    2.48
    quoted
    2.44
     reproducing
    2.39
     Reprodu
    2.27
     reprodu
    2.23
     reprinted
    2.23
    Activations Density 0.094%

    No Known Activations