© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 4024
    Prev
    Next
    INDEX
    Explanations

    surprising and unexpected

    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
    ançaise
    0.37
    rsfs
    0.36
     কামনা
    0.34
    uerite
    0.34
    Dv
    0.34
    佞
    0.34
     الو
    0.33
     ناقص
    0.33
    戊
    0.33
    ahlt
    0.33
    POSITIVE LOGITS
     surprising
    3.75
     surprise
    3.63
     surprised
    3.59
     überras
    3.47
     surprises
    3.38
     sorprend
    3.25
     surpr
    3.14
     sorpresa
    3.13
     unexpected
    3.11
    surprise
    3.08
    Activations Density 0.164%

    No Known Activations