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. 56
    Prev
    Next
    INDEX
    Explanations

    free to choose

    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
     Serv
    -0.78
     Lul
    -0.77
    рисо
    -0.75
    炔
    -0.75
     Russland
    -0.73
    Zü
    -0.73
     PAND
    -0.72
    Samson
    -0.72
     miró
    -0.72
    🧗
    -0.72
    POSITIVE LOGITS
    onomous
    0.87
     Halliday
    0.82
    य़
    0.79
    Companies
    0.77
    :"#
    0.75
     wc
    0.75
    ຣ
    0.75
    uroy
    0.74
     tajem
    0.74
     jahre
    0.73
    Activations Density 0.003%

    No Known Activations