© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58765
    Prev
    Next
    INDEX
    Explanations

    German preposition "zu"

    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
    {
    -3.44
     verbess
    -2.89
    燉
    -2.81
    ),
    -2.78
    鬭
    -2.77
    铼
    -2.69
    柃
    -2.69
    倧
    -2.66
     bogor
    -2.64
     bestehende
    -2.64
    POSITIVE LOGITS
     painstaking
    2.67
    Ꮏ
    2.63
     technologically
    2.59
    ’
    2.59
     heartwarming
    2.58
     femeninos
    2.58
    u
    2.45
    勿論
    2.45
     crée
    2.44
     éton
    2.42
    Activations Density 0.002%

    No Known Activations