© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130538
    Prev
    Next
    INDEX
    Explanations

    programming constructs and libraries

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

    The neuron activates on COM interop and type‐library terminology (e.g. BSTR, SysAllocString, TypeLib, Var, COM server, InProcServer, CLSID, GUID).

    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
     oxígeno
    -1.46
    不管是
    -1.43
    是非常
    -1.43
    我没有
    -1.41
    }}^{
    -1.39
    
    -1.39
    这不是
    -1.38
     зрения
    -1.37
     多少
    -1.36
     holdt
    -1.36
    POSITIVE LOGITS
    dungen
    1.30
    那种
    1.30
     mere
    1.24
    barang
    1.23
     %
    1.22
    jedi
    1.20
    bigliamento
    1.20
     möchten
    1.19
     you
    1.17
    {
    1.16
    Activations Density 0.025%

    No Known Activations