© 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. 231952
    Prev
    Next
    INDEX
    Explanations

    investment and finance terms

    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
     która
    0.52
    甪
    0.52
     caractéristique
    0.51
     Brion
    0.51
     ஒருவர்
    0.47
     fatta
    0.46
     koja
    0.45
     fondamental
    0.45
     která
    0.45
    浮か
    0.45
    POSITIVE LOGITS
     Н
    0.46
     Investment
    0.44
     ఆర్థిక
    0.43
     investment
    0.41
     Investments
    0.41
     aggressively
    0.40
     investments
    0.40
    XVI
    0.40
     sentenced
    0.39
    Investment
    0.39
    Activations Density 0.000%

    No Known Activations