© 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. 98284
    Prev
    Next
    INDEX
    Explanations

    beginning of texts

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

    The neuron strongly activates on occurrences of the identifier “Collections” (as in C# using-directive namespace imports like System.Collections).

    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
    millan
    -0.82
     Physical
    -0.79
    walt
    -0.78
    ]=="
    -0.76
    phylactic
    -0.74
    cembre
    -0.73
     Intra
    -0.72
    订阅
    -0.72
     supplying
    -0.71
     トヨタ
    -0.71
    POSITIVE LOGITS
     VOID
    0.91
    ビット
    0.85
    coroutine
    0.78
     中國
    0.76
     namespace
    0.73
    Void
    0.71
     WOULD
    0.71
    WaitFor
    0.71
    ↓↓
    0.70
    ogenesis
    0.70
    Activations Density 0.003%

    No Known Activations