© 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. 22-GEMMASCOPE-RES-131K
    4. 9603
    Prev
    Next
    INDEX
    Explanations

    one to another

    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_22/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
     and
    -2.11
    の準備
    -1.88
    をしました
    -1.61
    えっ
    -1.57
    に戻る
    -1.54
    すみません
    -1.52
     enchufe
    -1.41
    の方に
    -1.41
    を目指す
    -1.41
    つづく
    -1.39
    POSITIVE LOGITS
    そして
    1.45
    つまり
    1.41
    は
    1.33
    があり
    1.29
    風景
    1.23
    饅
    1.22
    なので
    1.21
     during
    1.20
    捩
    1.20
    を
    1.18
    Activations Density 0.021%

    No Known Activations