© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10949
    Prev
    Next
    INDEX
    Explanations

    size parameter or variable

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

    The neuron responds to C/C++ style integral type tokens of the form “size_<digits>_t” (e.g. size_364_t, size_320_t, etc.).

    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
     on
    -1.74
    梘
    -1.60
    UGHTER
    -1.52
     publicado
    -1.48
    ли
    -1.45
     becomes
    -1.43
     системой
    -1.43
     further
    -1.41
    ization
    -1.38
     includes
    -1.38
    POSITIVE LOGITS
    Apesar
    1.65
    6
    1.64
    んだから
    1.55
    Depois
    1.52
    私が
    1.49
    Примі
    1.47
    Até
    1.45
    僕が
    1.44
     plupart
    1.41
    Жит
    1.41
    Activations Density 0.005%

    No Known Activations