© 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. 10-GEMMASCOPE-RES-131K
    7. 65635
    Prev
    Next
    INDEX
    Explanations

    code, idioms, and studies

    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_10/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
    (
    -1.65
    Mereka
    -1.63
     של
    -1.62
     "/",
    -1.59
    Kemudian
    -1.58
    aur
    -1.57
    Bahkan
    -1.53
    chte
    -1.51
     versión
    -1.51
    ",
    -1.50
    POSITIVE LOGITS
     berühmten
    1.91
     normalerweise
    1.71
     haupts
    1.68
     necessario
    1.63
     kostet
    1.61
     vorliegenden
    1.59
    relatively
    1.59
     zwanzig
    1.58
     geprü
    1.57
     einzigartigen
    1.57
    Activations Density 0.000%

    No Known Activations