© 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. 11666
    Prev
    Next
    INDEX
    Explanations

    operable / operand

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

    the word "operand" or "operands" in technical programming and mathematical contexts.

    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
    '
    -3.22
    ᾔ
    -2.59
     '
    -2.58
    </b>
    -2.48
    のは
    -2.44
    1
    -2.20
    ти
    -2.19
     But
    -2.17
    archiwizowane
    -2.11
    「
    -2.03
    POSITIVE LOGITS
    ↵↵
    3.97
    
    2.92
     copious
    2.69
    迨
    2.59
     メニュー
    2.47
    唞
    2.42
    なぜか
    2.39
    渼
    2.39
    情节
    2.36
    the
    2.33
    Activations Density 0.001%

    No Known Activations