© 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. 121338
    Prev
    Next
    INDEX
    Explanations

    non-English languages

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

    adding, updating, deleting, processing

    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
    单个
    0.38
    setChecked
    0.38
     horseshoe
    0.37
     welds
    0.36
    焊
    0.36
     detail
    0.35
     individually
    0.35
    单一
    0.35
    埔
    0.35
     Wel
    0.35
    POSITIVE LOGITS
     समस्त
    0.39
    нтов
    0.39
    ardia
    0.38
     klaar
    0.38
     паци
    0.38
    ocas
    0.37
     існу
    0.37
    列表
    0.37
    一覧
    0.37
    พร้อม
    0.37
    Activations Density 0.019%

    No Known Activations