© 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. 90815
    Prev
    Next
    INDEX
    Explanations

    use a, Authors, cards

    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
    Filename
    -0.68
     anterior
    -0.68
     ט
    -0.65
     Juanita
    -0.64
     Preise
    -0.64
     Jean
    -0.63
    Json
    -0.62
     Now
    -0.61
    start
    -0.61
    now
    -0.61
    POSITIVE LOGITS
    Rahul
    0.75
    ╔
    0.71
     Rahul
    0.70
     Wilt
    0.69
    LogService
    0.69
     McIl
    0.68
    ELEM
    0.68
    Runnable
    0.67
     matières
    0.66
    Eau
    0.66
    Activations Density 0.538%

    No Known Activations