© 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. 35679
    Prev
    Next
    INDEX
    Explanations

    Japanese and core 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_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
    の方も
    -1.48
    に見える
    -1.41
    ときは
    -1.40
     this
    -1.34
    ところに
    -1.30
    ほら
    -1.27
    為に
    -1.26
     and
    -1.26
    方に
    -1.24
     Einfluß
    -1.23
    POSITIVE LOGITS
    <bos>
    1.60
    崭
    1.41
    醍
    1.39
    pherals
    1.33
    脍
    1.31
    を
    1.28
    そういった
    1.27
    それも
    1.24
    しかも
    1.23
    加減
    1.23
    Activations Density 0.008%

    No Known Activations