© 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. 53-GEMMASCOPE-2-RES-262K
    7. 37328
    Prev
    Next
    INDEX
    Explanations

    contempt, disdain, scorn, despising

    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_53_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
     марке
    0.41
     Hurt
    0.38
     சேர்க்க
    0.38
    蟹
    0.38
     привіт
    0.37
     cabins
    0.37
     Guerr
    0.36
     ملا
    0.36
    Equity
    0.35
     Pacífico
    0.35
    POSITIVE LOGITS
     contempt
    2.31
     disdain
    2.09
     scorn
    1.95
     despise
    1.59
     despised
    1.36
    蔑
    1.35
     sne
    1.30
     scoff
    1.22
     condesc
    1.14
     dispar
    1.13
    Activations Density 0.028%

    No Known Activations