© 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. 22172
    Prev
    Next
    INDEX
    Explanations

    the noun after common preceding word

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

    multilingual proper nouns or phrases

    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
    覧
    0.46
    tablename
    0.45
     でも
    0.42
     或者
    0.41
    DEST
    0.41
    আই
    0.40
    dbname
    0.40
     чыга
    0.40
    order
    0.39
    pathname
    0.39
    POSITIVE LOGITS
    जनिक
    0.44
    േഷന്‍
    0.43
    utiérrez
    0.42
    积极
    0.42
    纣
    0.42
     atuação
    0.42
     विरोधी
    0.42
    बिलिटी
    0.42
     zespo
    0.42
    电机
    0.41
    Activations Density 0.000%

    No Known Activations