© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12943
    Prev
    Next
    INDEX
    Explanations

    code generation and data structures

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

    memory management and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    讒
    0.66
    鄉
    0.65
    グルメ
    0.63
    ホテル
    0.61
    飯店
    0.61
    麗
    0.60
    サロン
    0.60
    銀座
    0.60
    豔
    0.60
    覽
    0.59
    POSITIVE LOGITS
     memcpy
    0.82
     malloc
    0.79
    Malloc
    0.78
     IntPtr
    0.78
     syscall
    0.77
     DCHECK
    0.77
    malloc
    0.72
    Ptr
    0.72
    编译器
    0.70
     llvm
    0.69
    Activations Density 0.120%

    No Known Activations