© 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. 66406
    Prev
    Next
    INDEX
    Explanations

    maps.googleapis.com

    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
     as
    -0.79
     MessageBoxIcon
    -0.79
     other
    -0.78
    getContent
    -0.75
     at
    -0.73
     enable
    -0.69
     =
    -0.69
     Ke
    -0.68
    Files
    -0.68
     Martin
    -0.68
    POSITIVE LOGITS
     zeigten
    0.82
     periodical
    0.81
    pēc
    0.80
    HeaderComponent
    0.80
     clipboard
    0.79
     Notch
    0.79
    ABET
    0.78
    lasma
    0.78
    autonomie
    0.78
    чехол
    0.77
    Activations Density 0.002%

    No Known Activations