© 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. 48129
    Prev
    Next
    INDEX
    Explanations

    licensed software, or foundation versions

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

    The neuron fires strongly on occurrences of “Threading” (as in using System.Threading) 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_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
    覦
    -0.76
    gettimeofday
    -0.73
     Ext
    -0.67
     ext
    -0.67
     pasada
    -0.66
    PROCEDURE
    -0.64
    nota
    -0.64
     deine
    -0.63
     nello
    -0.63
     pass
    -0.63
    POSITIVE LOGITS
    请问
    0.79
    cheduled
    0.72
     Prozesse
    0.69
    PEAT
    0.69
    çage
    0.68
     Mestre
    0.68
    請問
    0.68
     feldspar
    0.68
    größern
    0.68
     manag
    0.68
    Activations Density 0.076%

    No Known Activations