© 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. 48479
    Prev
    Next
    INDEX
    Explanations

    conditional or temporal clauses

    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
    However
    0.62
    ،
    0.57
    $,
    0.55
     However
    0.55
    however
    0.55
    ',
    0.53
    ș
    0.53
    然而
    0.53
    последствии
    0.53
    ጨማሪ
    0.52
    POSITIVE LOGITS
     নিম্নলিখিত
    0.44
     saddhim
    0.44
     sebuah
    0.44
     ={
    0.43
     Engen
    0.42
     ¬
    0.42
    ちょっと
    0.41
     व्याज
    0.41
     azienda
    0.41
     একটা
    0.40
    Activations Density 0.049%

    No Known Activations