© 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. 69916
    Prev
    Next
    INDEX
    Explanations

    Q: followed by colon

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

    The neuron fires on technical‐analysis headings or phrases in market commentary—specifically multiword terms like “Daily Supply Zone,” “break above the highs,” and similar supply‐zone/breakout jargon.

    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
     Resistance
    -0.81
     resistance
    -0.75
    振
    -0.74
     Besten
    -0.73
     regions
    -0.73
    躲
    -0.73
    adalajara
    -0.71
    ктория
    -0.71
     sprintf
    -0.70
    ких
    -0.70
    POSITIVE LOGITS
    曲线
    0.87
    ㄚ
    0.87
     UAB
    0.86
     Ако
    0.80
    ıyoruz
    0.80
    叹了口气
    0.80
    ieso
    0.80
    منون
    0.79
    了嗎
    0.79
    等着
    0.79
    Activations Density 0.001%

    No Known Activations