© 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. 57101
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

    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
    2
    0.41
     leaders
    0.40
     magie
    0.40
    会将
    0.39
     为了
    0.39
     linker
    0.38
    Leaders
    0.37
    1
    0.37
     params
    0.37
    为了
    0.37
    POSITIVE LOGITS
     দৃশ্য
    0.43
    ﭥ
    0.40
    cott
    0.40
     দত্ত
    0.40
    dwell
    0.39
     वर्तमान
    0.38
    amist
    0.38
     স্থাপিত
    0.38
     όταν
    0.38
    currentPage
    0.37
    Activations Density 0.028%

    No Known Activations