© 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. 10-GEMMASCOPE-RES-131K
    4. 9389
    Prev
    Next
    INDEX
    Explanations

    Anaerobic, Spain, <?php, 1

    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
     This
    -1.49
    नलोड
    -1.47
     =\
    -1.40
    เขา
    -1.39
     don
    -1.36
     Einige
    -1.34
     другими
    -1.34
     \%$,
    -1.33
    EDING
    -1.31
    brigens
    -1.30
    POSITIVE LOGITS
     perfectos
    1.54
    还要
    1.50
    klart
    1.48
     prévoir
    1.44
     stratég
    1.42
     bonitos
    1.41
     intégrée
    1.41
     diseñados
    1.39
    ighed
    1.38
     koszulka
    1.38
    Activations Density 0.000%

    No Known Activations