© 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-16K
    7. 1328
    Prev
    Next
    INDEX
    Explanations

    appear, happens

    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
    在
    3.33
     인해
    2.87
    ર
    2.64
    에
    2.46
    써
    2.43
    ीन
    2.40
    𝐛
    2.40
    smanship
    2.39
    𝐲
    2.37
     rattle
    2.33
    POSITIVE LOGITS
    Під
    3.04
    있는
    2.59
     продаже
    2.58
     номе
    2.56
     marchés
    2.53
     localised
    2.50
     entdecken
    2.48
     boroughs
    2.47
    न्दावन
    2.43
    Спољашње
    2.40
    Activations Density 0.236%

    No Known Activations