© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1485
    Prev
    Next
    INDEX
    Explanations

    commercial or mainstream

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

    This neuron detects idiomatic expressions that describe moderate or non-mainstream cultural taste (e.g. “middle brow,” “off the beaten path”).

    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
    ungi
    -0.93
    ragend
    -0.85
    nito
    -0.84
    mAuth
    -0.83
    bảng
    -0.81
     unique
    -0.81
    原始
    -0.80
    unique
    -0.79
    ytä
    -0.79
    Shaders
    -0.79
    POSITIVE LOGITS
     commercial
    2.45
    commercial
    2.17
     komer
    1.96
     mainstream
    1.87
     commercially
    1.80
     коммер
    1.80
     Commercial
    1.75
     commerciale
    1.75
    Commercial
    1.71
    商業
    1.71
    Activations Density 0.080%

    No Known Activations