© 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. 2721
    Prev
    Next
    INDEX
    Explanations

    physical document or print

    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
    âteaux
    -0.75
    árias
    -0.73
    чиком
    -0.71
     الرياض
    -0.71
    TokenNameLPAREN
    -0.71
    してしまった
    -0.70
    jumu
    -0.69
    繃
    -0.68
     Barnard
    -0.67
     Ashok
    -0.67
    POSITIVE LOGITS
     printed
    3.98
     paper
    3.50
     print
    3.31
     physical
    3.28
    printed
    3.09
    Printed
    3.06
     Printed
    2.97
    紙
    2.84
    physical
    2.80
     бума
    2.69
    Activations Density 0.111%

    No Known Activations