© 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. 45223
    Prev
    Next
    INDEX
    Explanations

    ui components: alert, panel, table

    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
    <0xF4>
    -0.83
    raised
    -0.79
    ülő
    -0.76
     Dragons
    -0.75
    enschutzer
    -0.74
    sburg
    -0.73
    wargs
    -0.72
     DAM
    -0.71
    loud
    -0.71
     browns
    -0.71
    POSITIVE LOGITS
     Ihm
    0.78
    ataan
    0.75
     call
    0.74
    網路
    0.72
     alert
    0.69
    cazione
    0.65
     haline
    0.65
     imprimé
    0.65
     проєкту
    0.65
     Repr
    0.64
    Activations Density 0.048%

    No Known Activations