© 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. 38284
    Prev
    Next
    INDEX
    Explanations

    coding utf-8 declaration

    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
    endroit
    -0.71
    不做
    -0.69
     membayar
    -0.69
     Place
    -0.66
     Execute
    -0.66
    蠔
    -0.66
     prezent
    -0.65
     gerçek
    -0.63
    欅
    -0.63
    thentic
    -0.62
    POSITIVE LOGITS
    smc
    0.72
    Asu
    0.70
     Aarhus
    0.68
     Schiffe
    0.68
     gestation
    0.68
    amilya
    0.66
    ships
    0.65
     Suz
    0.65
     Koro
    0.65
     kare
    0.64
    Activations Density 0.087%

    No Known Activations