© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53353
    Prev
    Next
    INDEX
    Explanations

    investors concerns and realizations

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

    geopolitical events affecting investors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    难
    0.60
    训练
    0.55
    鲔
    0.52
    长时间
    0.51
    荪
    0.50
    Density
    0.49
    髡
    0.49
    给她
    0.49
    瑷
    0.49
    殄
    0.48
    POSITIVE LOGITS
     investor
    0.89
     investors
    0.88
     bullish
    0.84
     speculators
    0.80
     traders
    0.79
     bearish
    0.78
     Reuters
    0.75
     rumores
    0.75
    ニュース
    0.71
     Investors
    0.71
    Activations Density 0.108%

    No Known Activations