© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59047
    Prev
    Next
    INDEX
    Explanations

    wherein, herein, whereby

    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
    lemmer
    -0.75
     Rene
    -0.75
    anio
    -0.71
    ｊ
    -0.71
     menjadi
    -0.68
     Deshalb
    -0.68
     sobald
    -0.66
     Otra
    -0.66
    如果
    -0.65
     Mek
    -0.65
    POSITIVE LOGITS
     wherein
    5.06
    wherein
    4.06
     whereby
    3.75
     therein
    3.73
     herein
    3.42
     فيها
    2.41
     darin
    2.31
     فيه
    2.25
     waarin
    2.22
    其中
    2.16
    Activations Density 0.258%

    No Known Activations