© 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. 11890
    Prev
    Next
    INDEX
    Explanations

    casting strings and objects

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

    method calls or type conversions that involve casting or converting to a specific type (particularly in programming contexts where "as" is used for type conversion or casting).

    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
    来自于
    -1.81
    짚
    -1.74
    上来
    -1.59
    开始了
    -1.59
     ہیں
    -1.53
     Verenig
    -1.47
    这类
    -1.43
     RESIDENCE
    -1.42
    芃
    -1.38
    试图
    -1.35
    POSITIVE LOGITS
    7
    1.69
    0
    1.67
    This
    1.66
    ("");
    1.65
    相比
    1.63
     También
    1.60
    asserole
    1.59
     Likewise
    1.51
    Additionally
    1.51
    Thus
    1.51
    Activations Density 0.008%

    No Known Activations