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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99806
    Prev
    Next
    INDEX
    Explanations

    personal notes observations messages

    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
     zwei
    -1.46
     BOTH
    -1.45
    kesan
    -1.45
    writeFileSync
    -1.45
     are
    -1.44
    釙
    -1.42
    нный
    -1.42
     apresenta
    -1.41
    guigu
    -1.41
    ому
    -1.41
    POSITIVE LOGITS
    personal
    2.05
    Personal
    1.74
     personal
    1.69
     подоб
    1.61
    個人
    1.58
    ブログ村
    1.53
    個人的
    1.46
     навіть
    1.45
     PERSONAL
    1.43
    次は
    1.37
    Activations Density 0.058%

    No Known Activations