© 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. 60126
    Prev
    Next
    INDEX
    Explanations

    sentence fragments and errors

    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
     ومن
    -0.87
    ồng
    -0.76
    Moth
    -0.72
    ガキ
    -0.69
    寺院
    -0.69
     workloads
    -0.68
     ähnliche
    -0.68
    ativní
    -0.68
    іе
    -0.67
    IPCC
    -0.67
    POSITIVE LOGITS
     comma
    1.34
     Fragments
    1.26
     fragments
    1.26
    fragments
    1.17
    run
    1.16
     compound
    1.15
     fragment
    1.14
     misplaced
    1.13
    Comma
    1.13
     run
    1.12
    Activations Density 0.044%

    No Known Activations