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. 160
    Prev
    Next
    INDEX
    Explanations

    scientific and technical writing

    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
     almost
    -0.83
    Переваги
    -0.79
     at
    -0.75
     made
    -0.74
    unlocked
    -0.73
     noise
    -0.72
     Geschichts
    -0.71
    集群
    -0.71
    节目
    -0.69
     Ռ
    -0.69
    POSITIVE LOGITS
    Pencil
    0.93
    Halo
    0.88
    global
    0.88
     halo
    0.88
     locaux
    0.87
     owners
    0.83
    BoxLayout
    0.80
     Halo
    0.79
    local
    0.78
     vidéos
    0.78
    Activations Density 0.009%

    No Known Activations