© 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. 54282
    Prev
    Next
    INDEX
    Explanations

    operating percent current

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

    The neuron fires on numeric financial figures (e.g. profit, net profit, millions in quarterly results).

    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
     deficiencies
    -0.85
     Gabrielle
    -0.82
     Poincar
    -0.81
    buatan
    -0.81
    Ofer
    -0.80
    ẳn
    -0.79
     himſelf
    -0.78
    每个
    -0.75
    vertret
    -0.75
     ira
    -0.74
    POSITIVE LOGITS
     Group
    1.08
     EUR
    0.97
     ambition
    0.96
    Gregor
    0.95
     €
    0.94
     grupo
    0.91
     guidance
    0.87
     impairment
    0.85
    الثة
    0.84
    DMETHOD
    0.84
    Activations Density 0.010%

    No Known Activations