© 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. 22-GEMMASCOPE-RES-131K
    7. 95778
    Prev
    Next
    INDEX
    Explanations

    setting up or defining something

    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
    <bos>
    -1.74
    その
    -1.57
     jego
    -1.45
    それは
    -1.36
     Redewendung
    -1.34
    參考資料
    -1.34
    段时间
    -1.31
    tidumbre
    -1.27
    紡
    -1.26
    これは
    -1.25
    POSITIVE LOGITS
     the
    2.19
     your
    1.68
    ようです
    1.52
    にほんブログ村
    1.50
    ほら
    1.49
    ところに
    1.48
    えっ
    1.48
    来週
    1.45
    うわ
    1.40
    konos
    1.38
    Activations Density 0.047%

    No Known Activations