© 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. 29-GEMMASCOPE-2-RES-16K
    7. 1885
    Prev
    Next
    INDEX
    Explanations

    português e conversar

    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_29_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
     بي
    2.14
     غير
    2.06
     سي
    2.04
     ك
    2.02
     جي
    1.98
     هي
    1.97
     ي
    1.97
     يا
    1.95
     دين
    1.91
     الك
    1.91
    POSITIVE LOGITS
     pessoas
    3.07
     algumas
    3.04
     não
    3.03
     também
    3.02
     ainda
    2.97
     você
    2.91
    não
    2.82
     quantidade
    2.75
     água
    2.75
     muito
    2.75
    Activations Density 0.061%

    No Known Activations