© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11536
    Prev
    Next
    INDEX
    Explanations

    subject and verb agreement

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ཌ
    1.11
    殆
    1.08
     Pirelli
    1.08
    𝙱
    1.08
    
    1.07
    ༅
    1.07
    Ⴎ
    1.07
    ᒎ
    1.06
    牛乳
    1.06
    機器
    1.05
    POSITIVE LOGITS
    a
    1.19
    awaited
    1.10
     sentence
    1.09
     eso
    1.07
     главной
    1.04
     ipsum
    1.01
    इस
    1.00
    prav
    1.00
    詞
    1.00
    l
    0.99
    Activations Density 0.191%

    No Known Activations