© 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. 9127
    Prev
    Next
    INDEX
    Explanations

    negative judgments after 'be' verbs

    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
    덬
    0.50
    🫠
    0.47
    🥲
    0.44
     objectively
    0.43
     ✨
    0.43
     curated
    0.41
    Despite
    0.40
     ит
    0.39
    ㅔ
    0.39
     vibes
    0.39
    POSITIVE LOGITS
     predominate
    0.60
     bogus
    0.59
     outrageous
    0.58
     worthless
    0.56
     tuff
    0.56
     disgraceful
    0.56
     incons
    0.55
     frightening
    0.54
     temor
    0.54
     phony
    0.53
    Activations Density 0.005%

    No Known Activations