© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 8274
    Prev
    Next
    INDEX
    Explanations

    witnesses and testimony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     optimizes
    0.55
     axially
    0.52
     स्वादिष्ट
    0.51
     optimizations
    0.48
     optimized
    0.48
     élytres
    0.48
     enables
    0.47
    ൗ
    0.47
     processor
    0.46
    optimized
    0.46
    POSITIVE LOGITS
     witnesses
    1.70
     Witnesses
    1.61
     witness
    1.45
     testigos
    1.45
    Witness
    1.38
     Witness
    1.29
    witness
    1.26
     свиде
    1.23
     témoins
    1.18
     testemun
    1.16
    Activations Density 0.004%

    No Known Activations