© 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. 57864
    Prev
    Next
    INDEX
    Explanations

    phrases completing common statements

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

    even relative conditions

    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
     সন্তানদের
    0.54
     öğretmen
    0.46
    的学生
    0.45
     বক্তব
    0.44
     বক্তব্য
    0.43
    沅
    0.43
     힘들
    0.43
    解释
    0.42
     শিক্ষক
    0.42
     চাঁদ
    0.42
    POSITIVE LOGITS
     underwriters
    0.46
    וד
    0.46
    ﻮ
    0.42
    ˡ
    0.42
     this
    0.42
    きっと
    0.42
    Another
    0.41
     improvisation
    0.40
    ̉
    0.40
    ب
    0.40
    Activations Density 0.001%

    No Known Activations