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. 230
    Prev
    Next
    INDEX
    Explanations

    legal contexts and Q&A format

    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
    期刊论文
    -0.88
     dinámica
    -0.87
    不吃
    -0.86
    Useless
    -0.82
    eniably
    -0.82
    凄く
    -0.81
    ڦ
    -0.78
     nemus
    -0.78
    έρα
    -0.77
     estratégico
    -0.77
    POSITIVE LOGITS
    Manager
    0.85
    Planet
    0.83
    CHARGE
    0.83
     charge
    0.83
     במק
    0.79
    似
    0.79
    Family
    0.77
    pump
    0.75
    Hold
    0.74
    О
    0.74
    Activations Density 0.008%

    No Known Activations