© 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. 9960
    Prev
    Next
    INDEX
    Explanations

    specific words followed by spaces or punctuation

    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
    -2.02
    どうやって
    -2.00
     be
    -1.82
    どれだけ
    -1.50
    Why
    -1.49
     allerdings
    -1.48
    散策
    -1.46
    遊ぶ
    -1.45
     T
    -1.43
    instead
    -1.41
    POSITIVE LOGITS
    étiques
    1.46
     nimmer
    1.44
    ggy
    1.43
    (||
    1.42
     namesake
    1.40
    thè
    1.39
     reise
    1.39
    🅲
    1.38
    ísticos
    1.38
    acji
    1.38
    Activations Density 0.134%

    No Known Activations