© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43506
    Prev
    Next
    INDEX
    Explanations

    parenting or parenthood

    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_10/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
    '
    -3.28
     humeur
    -2.33
    伋
    -2.28
    才行
    -2.22
    呔
    -2.17
     ของ
    -2.13
    鸚
    -2.09
     timmar
    -2.06
    Ruju
    -2.03
    的吗
    -2.03
    POSITIVE LOGITS
    We
    2.69
         
    2.52
    ("
    2.36
    叱
    2.34
    they
    2.34
     t
    2.27
    ↵↵
    2.22
    頻繁
    2.14
    );
    2.13
    をする
    2.11
    Activations Density 0.003%

    No Known Activations