Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8193
    Prev
    Next
    INDEX
    Explanations

    "exports" followed by comma or "s"

    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
    Builder
    -0.76
     sinusoidal
    -0.72
    σ
    -0.69
     Kig
    -0.68
    IndexOf
    -0.68
    LANE
    -0.67
    UX
    -0.67
    izando
    -0.67
     Tarzan
    -0.67
    Lane
    -0.66
    POSITIVE LOGITS
     estacion
    0.74
     Gemini
    0.64
     akhir
    0.64
     перемен
    0.62
    Saturn
    0.62
    Mats
    0.62
    pezi
    0.62
    ORIGINAL
    0.61
     Informasi
    0.60
     tindak
    0.60
    Activations Density 0.053%

    No Known Activations