© 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. 158800
    Prev
    Next
    INDEX
    Explanations

    couple followed by relationship verbs

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

    determining relative clauses

    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
    </em>
    0.49
    ’
    0.48
     божомолу
    0.47
     զ
    0.44
     масштаб
    0.41
    </th>
    0.41
     ө
    0.41
    iances
    0.41
    ンテ
    0.41
    </i>
    0.40
    POSITIVE LOGITS
     Woche
    0.54
    ۇل
    0.52
    琅
    0.52
     অভিষ
    0.51
    লেন
    0.50
    ंगत
    0.50
     kuj
    0.49
     चौथे
    0.49
     murdering
    0.48
    أس
    0.48
    Activations Density 0.000%

    No Known Activations