© 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. 103371
    Prev
    Next
    INDEX
    Explanations

    loaned or transferred

    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
    ecan
    -0.67
    颔
    -0.66
    ECON
    -0.65
    gusted
    -0.63
     dbName
    -0.63
     Schwan
    -0.63
     rv
    -0.62
    kop
    -0.62
    ordes
    -0.60
     Bereiche
    -0.60
    POSITIVE LOGITS
    dialogs
    0.73
    adine
    0.71
     Zie
    0.71
    coeur
    0.70
    Extend
    0.68
    gehenden
    0.68
     Dami
    0.67
    🏗
    0.66
     предложение
    0.65
    зя
    0.65
    Activations Density 0.100%

    No Known Activations