© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12266
    Prev
    Next
    INDEX
    Explanations

    of followed by determiners/pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ท์
    3.14
    b
    2.78
    います
    2.71
    ds
    2.70
    부터
    2.58
    もちろん
    2.55
    nen
    2.52
     ∠
    2.51
    f
    2.45
    ية
    2.42
    POSITIVE LOGITS
    ات
    3.49
    ीय
    2.99
    ূট
    2.80
     sudden
    2.57
    ים
    2.51
    बॉल
    2.48
    燾
    2.43
    க்கொண்டு
    2.40
    ЦИ
    2.40
    이
    2.40
    Activations Density 0.011%

    No Known Activations