© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14894
    Prev
    Next
    INDEX
    Explanations

    button click interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     উৎপাদন
    0.99
    ட்சி
    0.92
    簽
    0.91
     production
    0.90
     revitalization
    0.84
    uzu
    0.84
     produzione
    0.83
     return
    0.82
    黎
    0.82
    生產
    0.82
    POSITIVE LOGITS
     najbli
    1.24
    ally
    1.15
     ആവശ്യമ
    1.02
    🄴
    1.02
    merchant
    1.01
    neural
    1.00
     earnest
    0.97
    迥
    0.96
     obstructing
    0.95
    bs
    0.95
    Activations Density 0.001%

    No Known Activations