© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38587
    Prev
    Next
    INDEX
    Explanations

    should be, expect, atleast

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

    expectation and obligation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    intent
    0.38
     внима
    0.36
    teman
    0.36
     привлека
    0.34
     unwittingly
    0.34
     zuk
    0.34
    ปริ
    0.34
    ⊙
    0.33
     Commit
    0.33
     наме
    0.33
    POSITIVE LOGITS
     কমপক্ষে
    0.68
    はず
    0.61
    应该是
    0.61
     atleast
    0.61
    至少
    0.60
     অন্তত
    0.58
    少なくとも
    0.57
     almeno
    0.54
     dovrebbe
    0.54
     normalement
    0.54
    Activations Density 0.092%

    No Known Activations