© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92719
    Prev
    Next
    INDEX
    Explanations

    broadcasting, satellite, DVB, North America

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

    This neuron detects technical specification tokens—particularly numbers, model names, and uppercase hardware/acronym sequences.

    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
     connectivity
    -0.75
    atitis
    -0.72
    Martinez
    -0.68
     transcriptional
    -0.68
    Carro
    -0.68
     трансформа
    -0.66
     потре
    -0.65
     позво
    -0.64
    iado
    -0.63
    どんどん
    -0.63
    POSITIVE LOGITS
     Legacy
    0.87
     LNB
    0.86
    병
    0.76
     CA
    0.75
    biet
    0.74
     IDENTIFICATION
    0.74
    éndole
    0.73
    brero
    0.73
     Dvor
    0.72
    ược
    0.70
    Activations Density 0.031%

    No Known Activations