© 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. 15760
    Prev
    Next
    INDEX
    Explanations

    exclamation of surprise or amazement

    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
     carr
    0.39
     вой
    0.39
     խ
    0.38
     Laugh
    0.38
     Joke
    0.38
     Prevalence
    0.37
    ("\"
    0.37
     Carr
    0.37
    Appellant
    0.36
     Carre
    0.36
    POSITIVE LOGITS
    😲
    0.80
     wow
    0.76
    Wow
    0.74
    😮
    0.73
     Wow
    0.71
    wow
    0.67
    WOW
    0.62
    😯
    0.62
     WOW
    0.61
    😳
    0.57
    Activations Density 0.007%

    No Known Activations