© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37916
    Prev
    Next
    INDEX
    Explanations

    two categories or types

    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
     this
    -2.48
     such
    -1.78
     it
    -1.54
     этого
    -1.38
     its
    -1.34
     такую
    -1.20
     other
    -1.17
     такое
    -1.17
    がこの
    -1.12
     этом
    -1.10
    POSITIVE LOGITS
     respectively
    1.82
    それぞれ
    1.80
     while
    1.73
     enquanto
    1.72
    respectively
    1.61
     mientras
    1.57
     mentre
    1.53
     whereas
    1.52
     keduanya
    1.52
    Whereas
    1.46
    Activations Density 0.115%

    No Known Activations