© 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. 22935
    Prev
    Next
    INDEX
    Explanations

    spinal cord injury, brain death, neurologic

    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
     brain
    1.38
    Brain
    1.30
     Brain
    1.26
    brain
    1.20
    脳
    1.17
    脑
    1.14
     ब्रेन
    1.12
    腦
    1.06
     моз
    1.00
     मस्तिष्क
    1.00
    POSITIVE LOGITS
    ন্ড
    0.41
    swell
    0.38
     message
    0.38
    haul
    0.37
     StatefulWidget
    0.37
    息
    0.37
     asalamualaikum
    0.37
     flourishing
    0.35
     लेती
    0.35
     Sorrow
    0.34
    Activations Density 0.002%

    No Known Activations