© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10095
    Prev
    Next
    INDEX
    Explanations

    introduces contrast

    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
    𝗯
    3.12
     menengah
    2.96
     Estudos
    2.94
    𝚊
    2.87
     alku
    2.84
    VAS
    2.83
    б
    2.80
     частиц
    2.79
     banked
    2.77
    𝚐
    2.74
    POSITIVE LOGITS
    िक
    3.64
    spaper
    3.09
    ia
    3.06
    ,\,\,\,\
    3.00
    𝑚
    2.96
    ются
    2.82
    ้
    2.78
    𝑒
    2.78
    ੀ
    2.77
    م
    2.76
    Activations Density 0.015%

    No Known Activations