© 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
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 65378
    Prev
    Next
    INDEX
    Explanations

    "Sacred"

    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
    炅
    0.45
    דם
    0.41
     বিস্মিত
    0.38
     Jealous
    0.37
     angered
    0.36
     Reboot
    0.36
     jealous
    0.36
     continued
    0.36
     Pediatr
    0.36
     संबोध
    0.35
    POSITIVE LOGITS
    弇
    0.46
     přid
    0.39
    海洋
    0.39
    င့်
    0.38
    OUTPUT
    0.38
    開発
    0.38
    ancas
    0.38
    車
    0.37
    luxury
    0.36
    寐
    0.36
    Activations Density 0.000%

    No Known Activations