© 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. 13710
    Prev
    Next
    INDEX
    Explanations

    connection variable in code

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

    The neuron fires on occurrences of the identifier “conn” (i.e. connection variables in code).

    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
    外界
    -2.89
     wybór
    -2.55
    تیجه
    -2.52
    𝔈
    -2.50
    附属
    -2.50
    vantaged
    -2.42
    甬
    -2.41
    觏
    -2.34
     другая
    -2.33
    外人
    -2.33
    POSITIVE LOGITS
    \
    3.13
    medriver
    2.81
    鰨
    2.52
    2
    2.48
    栳
    2.41
     fièvre
    2.38
    ra
    2.38
     météo
    2.38
     résine
    2.36
    踯
    2.36
    Activations Density 0.002%

    No Known Activations