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. 8422
    Prev
    Next
    INDEX
    Explanations

    enumeration and quantification

    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
    那一
    -1.21
    的那
    -1.07
    那种
    -1.00
    这一
    -0.96
    的一
    -0.90
     those
    -0.90
    ทั้ง
    -0.89
     サロン
    -0.88
     diverses
    -0.88
    這一
    -0.86
    POSITIVE LOGITS
    什么
    1.04
    ènes
    1.02
    帖最后由
    1.00
     participado
    1.00
     interesantes
    0.99
    ∅
    0.96
     caído
    0.96
    řeba
    0.95
    しか
    0.94
     profundas
    0.94
    Activations Density 0.003%

    No Known Activations