© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12210
    Prev
    Next
    INDEX
    Explanations

    regard, regarding, regarded

    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
    などなど
    -2.77
     脚
    -2.45
    的时候
    -2.41
     院
    -2.41
    </b>
    -2.36
     苑
    -2.36
    別人
    -2.34
    上記
    -2.33
     户
    -2.31
     gemein
    -2.30
    POSITIVE LOGITS
    .”
    3.09
    ’
    2.84
     
    2.83
    ，“
    2.31
    鄚
    2.28
    “
    2.25
    に行
    2.17
    ：“
    2.13
     permitem
    2.13
     Pantalla
    2.09
    Activations Density 0.013%

    No Known Activations