© 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. 1708
    Prev
    Next
    INDEX
    Explanations

    collocations and phrases

    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
     دیگری
    0.36
     rappers
    0.35
     D
    0.34
     አ
    0.34
     Official
    0.33
    也不会
    0.33
     മറ്റ്
    0.33
    その他の
    0.32
    Autres
    0.32
     M
    0.32
    POSITIVE LOGITS
    न्होंने
    0.34
     damals
    0.32
     форми
    0.32
     ubiquitin
    0.31
     годы
    0.30
     этом
    0.29
    봄
    0.29
     কাজটি
    0.28
    <unused2197>
    0.28
    那时
    0.28
    Activations Density 0.000%

    No Known Activations