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. 8327
    Prev
    Next
    INDEX
    Explanations

    successful completion

    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
     descubrió
    -1.02
    tainable
    -0.94
     from
    -0.94
     for
    -0.91
     ilustracji
    -0.90
    Belum
    -0.87
     bebas
    -0.87
    ρών
    -0.85
    вної
    -0.85
    クシー
    -0.85
    POSITIVE LOGITS
     successfully
    2.73
     successful
    2.22
     Successfully
    2.09
    Successfully
    2.06
     success
    2.00
     sucess
    1.85
     succes
    1.84
    successfully
    1.77
     успешно
    1.74
     SUCCESS
    1.68
    Activations Density 0.011%

    No Known Activations