© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2176
    Prev
    Next
    INDEX
    Explanations

    astonishment and surprise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    '];
    0.72
    CLUSTERED
    0.68
    耷
    0.67
     coval
    0.62
    Anyway
    0.60
     기울
    0.60
    旮
    0.59
    깃
    0.59
     每
    0.59
    댔
    0.58
    POSITIVE LOGITS
     surprise
    4.64
     surprised
    4.62
     surprises
    4.20
     surprising
    4.13
     shocked
    4.03
     shock
    3.84
    surprise
    3.82
     Surprise
    3.75
     sorpresa
    3.59
     astonishment
    3.59
    Activations Density 0.942%

    No Known Activations