© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3984
    Prev
    Next
    INDEX
    Explanations

    after events

    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
     किंवा
    1.01
     असतात
    0.96
     يا
    0.93
     અથવા
    0.92
     אי
    0.91
    或
    0.86
     یا
    0.84
     שי
    0.83
     vagy
    0.82
    または
    0.80
    POSITIVE LOGITS
    Ketika
    1.29
     당시
    1.28
     ocasião
    1.26
    Shortly
    1.26
     पश्चात
    1.25
     aftermath
    1.18
    当時
    1.17
     ocurrió
    1.17
    Após
    1.17
     immédiatement
    1.16
    Activations Density 0.006%

    No Known Activations