© 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. 57307
    Prev
    Next
    INDEX
    Explanations

    conjunctions and adverbs like but

    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
     כדי
    0.45
     importantes
    0.40
    ᖕ
    0.40
     ক্ষীণ
    0.40
    @@]
    0.39
    ੯
    0.39
     중요
    0.39
     junk
    0.39
     COOK
    0.39
    탉
    0.39
    POSITIVE LOGITS
    especially
    0.50
    issime
    0.49
    albeit
    0.48
    能够在
    0.47
    Especially
    0.47
    if
    0.46
     enough
    0.46
    shaft
    0.45
     nawet
    0.45
    也非常
    0.45
    Activations Density 0.059%

    No Known Activations