© 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. 34-GEMMASCOPE-RES-131K
    7. 102953
    Prev
    Next
    INDEX
    Explanations

    verbs and their endings

    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
     by
    -1.03
     from
    -1.00
    باع
    -0.92
     ecclesias
    -0.92
     through
    -0.91
     nowadays
    -0.90
     emphasize
    -0.89
    ！！」
    -0.85
     Paleozoic
    -0.85
    كرت
    -0.85
    POSITIVE LOGITS
    に入れ
    1.09
     transc
    1.05
    際は
    0.98
    感じで
    0.97
     rapide
    0.97
     prič
    0.97
     ซึ่ง
    0.97
    のではなく
    0.96
    に入れる
    0.94
    めっちゃ
    0.94
    Activations Density 0.011%

    No Known Activations