© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112080
    Prev
    Next
    INDEX
    Explanations

    memory allocation, usage, and systems

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

    the substring "mem" in programming code, particularly in contexts related to memory operations, functions, and variable names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects identifiers or tokens beginning with “mem,” marking memory‐related terms or function/macros like memmove, memset, and mem_* in code.

    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
     he
    -3.44
    .
    -3.28
     Hinblick
    -3.20
    </h3>
    -3.11
    ]
    -3.09
     ähnlichen
    -2.83
     We
    -2.70
     speziellen
    -2.69
     echten
    -2.69
     solchen
    -2.67
    POSITIVE LOGITS
    Выводы
    2.83
    焿
    2.70
     個室
    2.64
    鿬
    2.63
     eléct
    2.52
    Минусы
    2.52
    グルト
    2.47
    Подготовка
    2.45
    Заключение
    2.42
    龗
    2.41
    Activations Density 0.007%

    No Known Activations