© 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. 22-GEMMASCOPE-RES-131K
    7. 70723
    Prev
    Next
    INDEX
    Explanations

    code snippets and errors

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

    This neuron detects fully qualified Java/Android API names—i.e. dot-separated package and class identifiers like the Android support library paths.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Prest
    -0.84
     COUNTRIES
    -0.83
    اتب
    -0.82
     pele
    -0.81
     nap
    -0.81
     puissance
    -0.81
     materna
    -0.80
    헬
    -0.79
    助力
    -0.79
     varandra
    -0.78
    POSITIVE LOGITS
    何も
    0.95
     rijk
    0.92
     Demolition
    0.90
     moschino
    0.90
     voordeel
    0.88
     желание
    0.87
    関する
    0.86
     kullanılır
    0.85
     sogni
    0.85
    >>()
    0.85
    Activations Density 0.014%

    No Known Activations