© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9534
    Prev
    Next
    INDEX
    Explanations

    surprise and shock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     고민
    0.55
     })(
    0.53
    煩
    0.53
     asignatura
    0.52
     itch
    0.50
     vign
    0.50
     TestCase
    0.50
     worrisome
    0.50
    ర్థి
    0.49
    锲
    0.49
    POSITIVE LOGITS
     shocked
    2.67
     surprise
    2.64
     surprised
    2.63
     shock
    2.61
    Shock
    2.48
     Shock
    2.42
    shock
    2.38
     astonishment
    2.38
    惊讶
    2.36
     astonished
    2.33
    Activations Density 0.232%

    No Known Activations