© 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. 80772
    Prev
    Next
    INDEX
    Explanations

    code imports and comments

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

    This neuron detects Android‐specific Java package and import declarations (e.g., lines beginning with “package …” or “import android…”).

    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
    oba
    -0.83
    listData
    -0.78
     बे
    -0.76
    ICATED
    -0.73
     αὐτ
    -0.73
     discovery
    -0.71
    жит
    -0.69
    compras
    -0.69
    YOUTUBE
    -0.69
    busca
    -0.68
    POSITIVE LOGITS
     SDK
    1.07
     côn
    0.91
    SDK
    0.91
    ไซ
    0.84
    VolleyError
    0.83
     hummus
    0.81
     RoutedEventArgs
    0.80
    changeable
    0.80
    voort
    0.79
    reso
    0.78
    Activations Density 0.010%

    No Known Activations