© 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. 40-GEMMASCOPE-2-RES-262K
    7. 17774
    Prev
    Next
    INDEX
    Explanations

    exclamations of delight

    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_40_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
     :/
    0.60
     unavoid
    0.51
     తీవ్ర
    0.49
    😞
    0.49
    😑
    0.48
     unavoidable
    0.48
    😔
    0.47
     tbh
    0.47
    😥
    0.44
    很难
    0.44
    POSITIVE LOGITS
     rejoice
    1.13
     delighted
    1.10
     hoera
    1.09
    Yay
    0.98
     exciting
    0.95
     overjoyed
    0.95
     🎉
    0.95
     yay
    0.94
     excitedly
    0.93
     thrilled
    0.93
    Activations Density 0.006%

    No Known Activations