© 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. 98084
    Prev
    Next
    INDEX
    Explanations

    up to you, left to you

    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
     förr
    -0.83
    🎌
    -0.79
     nødvendig
    -0.75
    tação
    -0.75
     actuales
    -0.73
     Fug
    -0.73
    starttime
    -0.73
    denken
    -0.73
    给我
    -0.73
    ghted
    -0.73
    POSITIVE LOGITS
     up
    6.63
     upto
    3.23
    Up
    2.86
    up
    2.69
     Up
    2.61
    upto
    2.44
     left
    2.30
    ขึ้น
    2.20
     lên
    2.14
     вверх
    1.96
    Activations Density 0.029%

    No Known Activations