© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65972
    Prev
    Next
    INDEX
    Explanations

    financial movements and changes

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

    The neuron detects financial‐market terminology, especially words related to trading, hedging or speculating on future values (e.g. futures, price, value, hedge, speculate).

    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
    AlterField
    -0.84
    >--}}
    -0.81
     tabletop
    -0.81
    Appellant
    -0.79
    QUIT
    -0.78
    يديو
    -0.77
    iterran
    -0.77
    OffsetY
    -0.76
    řevě
    -0.76
    OnDelete
    -0.76
    POSITIVE LOGITS
     movements
    3.56
     movement
    3.30
     moves
    2.75
    movements
    2.67
     move
    2.59
     Movements
    2.58
    movement
    2.58
     Movement
    2.38
    Movement
    2.30
    Move
    2.23
    Activations Density 0.037%

    No Known Activations