© 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. 110671
    Prev
    Next
    INDEX
    Explanations

    function returns

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

    the keyword "return" in programming code, particularly in function definitions and control flow statements.

    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
     Когда
    -2.80
     Если
    -2.73
     raccont
    -2.72
     trovano
    -2.33
     Что
    -2.20
     andata
    -2.09
     attiva
    -2.08
    }$
    -2.06
    "});
    -2.03
     vuole
    -2.03
    POSITIVE LOGITS
     \
    2.72
    ჻
    2.33
    return
    2.31
    を確認
    2.14
    for
    2.13
    𖤍
    2.13
    ”
    2.02
     pour
    2.00
     строительство
    1.99
    AnchorStyles
    1.98
    Activations Density 0.006%

    No Known Activations