© 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. 12890
    Prev
    Next
    INDEX
    Explanations

    profit, wealth, and exploitation

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

    eager for profit and control

    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
     சுற்றுச்சூழல்
    0.50
    咘
    0.45
     احترام
    0.45
    ững
    0.44
    كلمنا
    0.43
     Gesundheit
    0.43
    Equipment
    0.41
    健康
    0.41
     nautical
    0.41
     সন্ব
    0.40
    POSITIVE LOGITS
     lucrative
    0.78
     profitable
    0.77
    覬
    0.75
     profit
    0.74
     profits
    0.70
    利益
    0.70
     хотят
    0.70
    profitable
    0.68
     selfish
    0.68
     хочет
    0.68
    Activations Density 0.178%

    No Known Activations