© 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. 126813
    Prev
    Next
    INDEX
    Explanations

    "As" followed by clauses or general statements

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

    Conditional statements starting with **If**

    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
    他にも
    0.45
     иной
    0.44
     рядом
    0.43
    Elle
    0.43
    хин
    0.43
    除了
    0.41
    不仅
    0.41
    伲
    0.41
    ่าย
    0.40
    不僅
    0.40
    POSITIVE LOGITS
     সেটাও
    0.47
     insgesamt
    0.41
    总体
    0.40
     nên
    0.39
     Gesamt
    0.38
     overall
    0.37
     jadi
    0.36
    所以在
    0.36
     dünyaya
    0.36
     donc
    0.35
    Activations Density 0.039%

    No Known Activations