© 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. 22-GEMMASCOPE-RES-131K
    7. 75222
    Prev
    Next
    INDEX
    Explanations

    technical indicators or formation

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

    This neuron responds to financial market analysis jargon, especially technical‐analysis terms and chart‐pattern references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ？！”
    -1.20
    understanding
    -1.20
     éviter
    -1.19
    later
    -1.19
     cucchiai
    -1.15
    쐈
    -1.13
    Increased
    -1.13
     gegebenen
    -1.09
    ！！！”
    -1.09
     DIFFERENT
    -1.08
    POSITIVE LOGITS
    breviations
    1.20
     jangka
    1.15
     Dezember
    1.10
     on
    1.09
     recently
    1.08
     we
    1.08
     vivía
    1.08
    Condol
    1.07
     venía
    1.07
     aktivitas
    1.06
    Activations Density 0.008%

    No Known Activations