© 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. 76312
    Prev
    Next
    INDEX
    Explanations

    EFI Shell protocol

    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
    educt
    -0.75
     أغ
    -0.74
     edición
    -0.72
     Hưng
    -0.70
     اللب
    -0.70
     Mughal
    -0.70
     revend
    -0.69
     نصف
    -0.69
    vira
    -0.68
     FAVORITE
    -0.68
    POSITIVE LOGITS
     guiding
    0.73
    导师
    0.71
     amb
    0.69
    amb
    0.63
    arsh
    0.61
    点头
    0.61
    Marshall
    0.60
    semaphore
    0.60
    ₁,
    0.59
     тен
    0.59
    Activations Density 0.081%

    No Known Activations