© 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. 98182
    Prev
    Next
    INDEX
    Explanations

    US, AZ, IN

    np_acts-logits-general · gemini-2.5-flash-lite

    the appearance of “en US” or similar language–country locale codes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    えっ
    -1.84
    さぁ
    -1.59
    無し
    -1.56
    ほら
    -1.55
    いえ
    -1.52
    すっ
    -1.48
    あぁ
    -1.45
     Of
    -1.45
    のお知らせ
    -1.42
    にします
    -1.38
    POSITIVE LOGITS
    <bos>
    1.66
    を
    1.53
    دانلود
    1.37
    Bjs
    1.36
    その
    1.36
     作り方
    1.31
     sommeil
    1.30
    توضیحات
    1.29
    がって
    1.28
    作り方
    1.27
    Activations Density 0.012%

    No Known Activations