© 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. 60434
    Prev
    Next
    INDEX
    Explanations

    switch case

    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
    кнул
    -0.82
    戬
    -0.82
    SSID
    -0.82
    িনি
    -0.79
    ailangan
    -0.78
    rici
    -0.77
     personaje
    -0.77
    гласно
    -0.76
     carga
    -0.76
     iterations
    -0.76
    POSITIVE LOGITS
     контей
    0.75
     gyms
    0.74
     الشاشة
    0.73
     Babylon
    0.72
    ises
    0.68
    メット
    0.68
    ​​
    0.68
     Guyana
    0.67
    Latch
    0.66
    ow
    0.65
    Activations Density 0.000%

    No Known Activations