© 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. 41388
    Prev
    Next
    INDEX
    Explanations

    programming concepts

    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
     to
    -1.83
     that
    -1.62
    игра
    -1.61
    things
    -1.51
     something
    -1.45
     mempel
    -1.45
    positories
    -1.39
     where
    -1.38
     kartą
    -1.35
    PRWEB
    -1.34
    POSITIVE LOGITS
     เรา
    1.45
    Biografi
    1.40
    を見つけ
    1.36
    Fakta
    1.35
    Зно
    1.34
     οποίο
    1.29
     paff
    1.27
     ftate
    1.26
    andowski
    1.26
     terza
    1.26
    Activations Density 0.030%

    No Known Activations