© 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. 120772
    Prev
    Next
    INDEX
    Explanations

    [word] [preposition]

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

    sentence end punctuation

    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
    其他
    0.51
    אה
    0.47
     hạ
    0.47
    ưu
    0.45
    所有人
    0.45
    세요
    0.45
    홍
    0.45
     tiek
    0.44
    거든
    0.44
    기
    0.44
    POSITIVE LOGITS
    JOB
    0.49
     एकल
    0.48
     Escal
    0.47
     عب
    0.46
     رد
    0.46
    lovers
    0.46
     ব্য
    0.46
     Ε
    0.45
    tt
    0.45
    ENO
    0.44
    Activations Density 0.000%

    No Known Activations