© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 141
    Prev
    Next
    INDEX
    Explanations

    obligation and necessity

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

    must or need to

    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_16k_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
    <0x0D>
    0.22
    ။
    0.20
    ))
    0.20
    ។
    0.20
    \
    0.19
    のような
    0.19
     或
    0.19
    。
    0.19
    ｗ
    0.19
    ຈາກ
    0.19
    POSITIVE LOGITS
     be
    0.30
    要有
    0.29
     ต้อง
    0.28
     অবশ্যই
    0.28
     обязательно
    0.26
     carefully
    0.26
     помнить
    0.26
     beware
    0.26
     unbedingt
    0.25
    一定要
    0.24
    Activations Density 1.004%

    No Known Activations