© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144490
    Prev
    Next
    INDEX
    Explanations

    possession or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite

    understand prioritize ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dilemma
    0.43
    ավ
    0.40
    ޯ
    0.40
    льних
    0.39
    ем
    0.39
     comport
    0.39
    اج
    0.39
    بة
    0.39
    とき
    0.38
    ustible
    0.37
    POSITIVE LOGITS
    Objet
    0.52
     खूबसूरत
    0.50
    ﭥ
    0.49
     ეს
    0.48
     Chayin
    0.48
     这是
    0.48
     ის
    0.47
     enchanted
    0.47
     obfusc
    0.47
    Yves
    0.46
    Activations Density 0.002%

    No Known Activations