© 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. 70749
    Prev
    Next
    INDEX
    Explanations

    dictionary access with string keys

    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
    ’
    -2.39
    <bos>
    -2.28
     personalizadas
    -2.09
    などが
    -2.05
    そして
    -2.00
     those
    -2.00
    糞
    -2.00
     epitom
    -1.95
     some
    -1.88
     other
    -1.84
    POSITIVE LOGITS
    為に
    3.08
    えっ
    2.66
    鑁
    2.38
    すっ
    2.36
    場所で
    2.34
    で見る
    2.34
    事で
    2.30
    ところに
    2.22
    つづく
    2.19
     ซึ่ง
    2.16
    Activations Density 0.006%

    No Known Activations