© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27454
    Prev
    Next
    INDEX
    Explanations

    momentum and investing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    班牙
    0.42
    ικό
    0.40
    కునే
    0.40
    讥
    0.39
    Node
    0.39
    alary
    0.38
    竞争力
    0.38
    Fork
    0.38
     अस्तित्व
    0.37
    寻
    0.37
    POSITIVE LOGITS
     momentum
    0.77
     Momentum
    0.63
    momentum
    0.62
     transfer
    0.54
    пере
    0.49
     inertia
    0.48
     DRI
    0.47
     transfers
    0.45
     carry
    0.45
     trasfer
    0.44
    Activations Density 0.002%

    No Known Activations