© 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. 10-GEMMASCOPE-RES-131K
    7. 65094
    Prev
    Next
    INDEX
    Explanations

    punc. then verb

    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
     sogenannten
    -1.71
     for
    -1.63
     burbu
    -1.62
    diferentes
    -1.60
     pindah
    -1.59
     mulus
    -1.58
    wyżs
    -1.52
     cokelat
    -1.51
     segi
    -1.51
    इटम
    -1.50
    POSITIVE LOGITS
     and
    1.41
    6
    1.40
     Cacao
    1.37
     眼睛
    1.37
     tao
    1.28
     تحميل
    1.26
     хочется
    1.25
    看到
    1.22
    getragen
    1.19
    𓆉
    1.19
    Activations Density 0.038%

    No Known Activations