© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55811
    Prev
    Next
    INDEX
    Explanations

    style and code formatting

    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
     ihti
    -0.80
    パーティ
    -0.75
     Ausdrücke
    -0.74
    ▱
    -0.71
    Thomson
    -0.69
    DCE
    -0.69
     siff
    -0.69
     assi
    -0.69
    configure
    -0.69
     Nand
    -0.68
    POSITIVE LOGITS
    byes
    0.88
     terkait
    0.82
    cky
    0.81
    ؛
    0.79
     mahdollis
    0.78
    𝐛
    0.78
    PlaceHolder
    0.78
     concernant
    0.77
     root
    0.75
    INGS
    0.75
    Activations Density 0.011%

    No Known Activations