© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12890
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_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
    كلمنا
    0.47
    咘
    0.46
    Equipment
    0.42
    电子邮件
    0.42
    ững
    0.41
     solltest
    0.40
     جوړونکي
    0.40
     diskut
    0.40
    骢
    0.40
     thoughtful
    0.39
    POSITIVE LOGITS
     profit
    0.75
     selfish
    0.71
     lucrative
    0.70
     profits
    0.70
     profitable
    0.68
    利益
    0.63
     propaganda
    0.62
     profitability
    0.60
    利润
    0.60
    覬
    0.60
    Activations Density 0.160%

    No Known Activations