© 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. 34-GEMMASCOPE-RES-131K
    7. 48277
    Prev
    Next
    INDEX
    Explanations

    smart pointers and references

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

    The neuron fires on programming‐language type and template identifiers (e.g. map, Ptr, optional, function, memory) indicating C++ type or template usage.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     małe
    -0.80
    Between
    -0.80
     between
    -0.79
     nagyobb
    -0.77
     تغيير
    -0.76
     шесть
    -0.76
     necesitar
    -0.76
    ®
    -0.75
     Jahr
    -0.75
    おかしい
    -0.75
    POSITIVE LOGITS
     of
    0.96
     パーク
    0.90
    ĵo
    0.88
    ⣻
    0.87
    ashions
    0.87
     quali
    0.86
    ဉ
    0.84
    zahl
    0.84
    Ἕ
    0.84
    dade
    0.83
    Activations Density 0.008%

    No Known Activations