© 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. 249468
    Prev
    Next
    INDEX
    Explanations

    determiners and quantifiers followed by nouns

    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
    ᱐
    0.59
     পোকামাকড়
    0.59
    nT
    0.57
    wanted
    0.54
    ຈັດສົ່ງ
    0.54
     মুক্তিব
    0.54
     interstitiis
    0.54
     पत्रकारों
    0.54
    maskedTextBox
    0.53
    testimonial
    0.53
    POSITIVE LOGITS
    ↵
    0.61
    هد
    0.45
     Show
    0.45
     changer
    0.45
     FE
    0.43
     constant
    0.43
     Schluss
    0.43
     Sole
    0.42
    લ
    0.42
    ادی
    0.41
    Activations Density 0.000%

    No Known Activations