© 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. 10-GEMMASCOPE-RES-131K
    7. 102386
    Prev
    Next
    INDEX
    Explanations

    `<<` operator

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

    the left bit-shift operator "<<" in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’
    -2.97
    ↵↵
    -2.59
     Not
    -2.41
    Surprisingly
    -2.30
    過ぎる
    -2.28
    𖡼
    -2.20
     meningkat
    -2.17
    
    -2.16
    龊
    -2.16
    蘗
    -2.11
    POSITIVE LOGITS
    '
    3.38
    騭
    2.81
     插画
    2.72
    羕
    2.67
    馓
    2.48
    </i>
    2.39
    齮
    2.39
    \
    2.36
    {
    2.33
    ꪹ
    2.33
    Activations Density 0.003%

    No Known Activations