© 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. 64542
    Prev
    Next
    INDEX
    Explanations

    personal expenses

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

    The neuron detects mentions of extra monetary charges—words like “fees,” “costs,” “taxes,” and “charges.”

    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
    ROID
    -0.84
    jerne
    -0.82
     trod
    -0.82
    romp
    -0.81
    蛆
    -0.81
    mesin
    -0.81
     discontin
    -0.78
    NSY
    -0.77
    abon
    -0.76
     suffit
    -0.76
    POSITIVE LOGITS
     personal
    1.25
     meals
    1.24
    Personal
    1.06
     anything
    1.05
     any
    1.05
     Personal
    1.04
    personal
    1.01
    tips
    0.96
     food
    0.94
     camera
    0.93
    Activations Density 0.004%

    No Known Activations