© 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. 60096
    Prev
    Next
    INDEX
    Explanations

    file path operations

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

    The neuron detects C# “using” directives, especially those that import System.* namespaces.

    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
     they
    -1.62
    }=
    -1.50
     "
    -1.38
    =
    -1.34
    HEIGHT
    -1.30
    了一眼
    -1.28
     Mittwoch
    -1.27
     group
    -1.27
     their
    -1.26
    		
    -1.26
    POSITIVE LOGITS
    vamo
    1.48
     permukaan
    1.26
    ⬇
    1.19
    把它
    1.17
     Penyakit
    1.17
    どれだけ
    1.16
    غذ
    1.13
    These
    1.13
    "$_
    1.13
    ープン
    1.13
    Activations Density 0.360%

    No Known Activations