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. 21
    Prev
    Next
    INDEX
    Explanations

    file_get_contents, json_decode, parse

    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
     those
    -0.98
     pierdas
    -0.96
    ειτουργ
    -0.92
     any
    -0.85
     method
    -0.81
     biografias
    -0.81
     Rheinland
    -0.79
     but
    -0.79
     negras
    -0.79
     violent
    -0.77
    POSITIVE LOGITS
    ($
    0.94
     ſer
    0.88
    ฌ
    0.88
     éviter
    0.86
    zondere
    0.86
     chatbot
    0.85
    ulfon
    0.84
    habhar
    0.84
    🪳
    0.82
    Gus
    0.81
    Activations Density 0.016%

    No Known Activations