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. 8092
    Prev
    Next
    INDEX
    Explanations

    word beginnings `Helper`, `End`, `Bur`, `How`

    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
    也太
    -0.94
     także
    -0.74
    ୁ
    -0.73
    对其
    -0.73
     Pals
    -0.72
     Buds
    -0.72
     eher
    -0.71
    bura
    -0.71
     Vite
    -0.71
     Kens
    -0.71
    POSITIVE LOGITS
    Michigan
    0.88
     innovate
    0.86
    現役
    0.85
    seler
    0.82
    地下
    0.81
    gaben
    0.79
    愛知県
    0.79
    Ontario
    0.79
    运动员
    0.78
    ❦
    0.78
    Activations Density 0.010%

    No Known Activations