© 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. 71170
    Prev
    Next
    INDEX
    Explanations

    as type casts

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

    This neuron detects type‐casting expressions, especially the Swift “as?” optional down‐cast operator.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     декабря
    -1.88
     Cleanser
    -1.81
     lakini
    -1.74
    镡
    -1.73
     июля
    -1.73
     maart
    -1.70
    .」
    -1.66
     castel
    -1.65
     penghar
    -1.64
     UNIVERSIT
    -1.63
    POSITIVE LOGITS
     kleineren
    1.75
    However
    1.74
    ).
    1.74
    They
    1.69
    The
    1.65
     incredibly
    1.59
     wichtigen
    1.59
     größeren
    1.59
     一
    1.59
    )
    1.59
    Activations Density 0.006%

    No Known Activations