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. 191
    Prev
    Next
    INDEX
    Explanations

    problems and challenges

    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
    																										
    -0.81
    liers
    -0.81
    obox
    -0.81
    ṝ
    -0.80
    laundry
    -0.79
    mks
    -0.79
    providedIn
    -0.79
     фоль
    -0.78
    ştir
    -0.78
    ongeza
    -0.77
    POSITIVE LOGITS
    잦
    0.90
     hydra
    0.89
    kati
    0.82
    ข้อมูล
    0.81
     challenges
    0.80
    erle
    0.80
    ユーザー
    0.78
     continuous
    0.76
     climate
    0.75
    最近
    0.75
    Activations Density 0.014%

    No Known Activations