© 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. 74849
    Prev
    Next
    INDEX
    Explanations

    for then a pronoun

    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
    ﹕
    -1.68
     információk
    -1.54
    itato
    -1.47
     Biographie
    -1.42
    γωγ
    -1.39
    руем
    -1.38
     informée
    -1.32
    věř
    -1.32
     reemplazo
    -1.32
     inapropiados
    -1.32
    POSITIVE LOGITS
    {
    1.98
     you
    1.55
    al
    1.43
    en
    1.41
     then
    1.39
     pero
    1.37
     me
    1.35
     какого
    1.34
     keď
    1.32
    /
    1.28
    Activations Density 0.025%

    No Known Activations