© 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. 34-GEMMASCOPE-RES-131K
    4. 25756
    Prev
    Next
    INDEX
    Explanations

    german words starting with wer

    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
     مفص
    -0.78
     扇
    -0.72
     correos
    -0.70
    kopi
    -0.70
     جمه
    -0.70
    壇
    -0.69
    splitting
    -0.69
     transgression
    -0.69
    spending
    -0.68
     examination
    -0.67
    POSITIVE LOGITS
     ellas
    0.83
    macht
    0.83
    严肃
    0.75
     Wer
    0.75
    arem
    0.74
    `),
    0.74
     сериал
    0.73
     AXIS
    0.73
     кисло
    0.73
     souligne
    0.73
    Activations Density 0.016%

    No Known Activations