© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13148
    Prev
    Next
    INDEX
    Explanations

    Spanish suffixes or word endings

    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_17_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
    |$.
    0.96
    хема
    0.94
    Ан
    0.91
     Elast
    0.89
     кушымта
    0.89
     Optimize
    0.89
     सब्जियों
    0.88
    ান
    0.87
    Optimize
    0.86
    𝘽
    0.86
    POSITIVE LOGITS
    ning
    1.02
    nessy
    1.00
    nie
    0.99
    adin
    0.98
    istica
    0.95
    ner
    0.94
    ado
    0.93
    izada
    0.90
    izado
    0.90
    atae
    0.87
    Activations Density 0.317%

    No Known Activations