© 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. 31-GEMMASCOPE-2-RES-65K
    7. 49400
    Prev
    Next
    INDEX
    Explanations

    Valentine's Day, Romeo, Theseus

    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_31_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
    agamanam
    0.57
    媺
    0.42
    ேட்
    0.41
     milestones
    0.41
     Excellent
    0.40
     eBooks
    0.39
     Delicious
    0.39
     столь
    0.38
     benchmarks
    0.38
    ोतरी
    0.38
    POSITIVE LOGITS
    τική
    0.44
    乩
    0.43
     lakini
    0.43
    but
    0.42
     piloto
    0.42
    傛
    0.42
    lose
    0.42
     تشدد
    0.42
     أثناء
    0.42
     olvid
    0.41
    Activations Density 0.019%

    No Known Activations