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. 8064
    Prev
    Next
    INDEX
    Explanations

    street addresses and directions

    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
    而且
    -0.80
    ></
    -0.74
    曽
    -0.70
    活動
    -0.70
    QUÉ
    -0.69
     marinho
    -0.69
     CMR
    -0.67
    nami
    -0.66
    ources
    -0.66
    잇
    -0.66
    POSITIVE LOGITS
     päiv
    0.89
    的一天
    0.87
     Sixth
    0.80
     neighborhoods
    0.76
     pembayaran
    0.75
     airport
    0.75
     north
    0.74
     Airport
    0.73
     penghar
    0.73
     North
    0.72
    Activations Density 0.023%

    No Known Activations