© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 159
    Prev
    Next
    INDEX
    Explanations

    preposition "on" introducing context

    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_16k_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
    릭터
    0.86
    Error
    0.85
    usion
    0.84
    ে
    0.83
    ্ম
    0.83
    şik
    0.83
     обратиться
    0.80
    たくさん
    0.80
     dacă
    0.79
    তে
    0.79
    POSITIVE LOGITS
     behalf
    1.35
    िक्रमा
    0.96
    nections
    0.91
    ৈতিক
    0.86
    nection
    0.84
    n
    0.80
     occasion
    0.80
     الرغم
    0.79
     keresztül
    0.79
    etime
    0.78
    Activations Density 0.705%

    No Known Activations