© 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. 10-GEMMASCOPE-RES-131K
    7. 74974
    Prev
    Next
    INDEX
    Explanations

    org.apache, android.runtime, log4j

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

    This neuron detects namespace or package qualifiers in code, such as “org,” “net,” or other top‐level package tokens.

    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
     queridos
    -1.85
    eſ
    -1.84
     comien
    -1.81
     gracioso
    -1.76
     Because
    -1.66
     vengan
    -1.65
     sabias
    -1.65
    faatkan
    -1.62
     ".";
    -1.61
    テナンス
    -1.59
    POSITIVE LOGITS
    as
    1.92
    to
    1.84
     $
    1.75
    {~
    1.70
    not
    1.68
    もの
    1.63
    be
    1.62
     использовании
    1.61
    mathcal
    1.61
     more
    1.61
    Activations Density 0.001%

    No Known Activations