© 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. 103622
    Prev
    Next
    INDEX
    Explanations

    function parameters: types and errors

    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
    ۔
    -1.09
    ıyors
    -1.05
     latter
    -0.96
     みた
    -0.92
     ciepła
    -0.92
     powiet
    -0.92
    푆
    -0.90
     小学
    -0.89
    Referencia
    -0.88
    }}]{
    -0.86
    POSITIVE LOGITS
     []
    1.20
     but
    1.16
     int
    1.11
     www
    1.10
     in
    1.10
     [][]
    1.05
     string
    1.05
     ``
    1.03
     […]
    1.02
     *
    1.00
    Activations Density 0.035%

    No Known Activations