© 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. 17318
    Prev
    Next
    INDEX
    Explanations

    words before nouns or verbs

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

    try this

    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
    뭍
    0.46
    ändert
    0.42
    苓
    0.42
    น่า
    0.42
     getWorld
    0.40
     ComVisible
    0.40
    싫
    0.40
    ConnectionString
    0.40
     keine
    0.39
     rejects
    0.39
    POSITIVE LOGITS
     रिचार्ज
    0.50
     UAS
    0.50
     فوجی
    0.48
     എടു
    0.48
     octubre
    0.48
    了很多
    0.47
     hiz
    0.46
    katan
    0.46
    了不少
    0.46
     ó
    0.46
    Activations Density 0.000%

    No Known Activations