© 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. 40-GEMMASCOPE-2-RES-262K
    7. 193497
    Prev
    Next
    INDEX
    Explanations

    death and defeat

    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/layer_40_width_262k_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
     убий
    0.55
     killing
    0.50
     Killing
    0.49
    Killing
    0.48
     killings
    0.46
     giết
    0.46
    莧
    0.44
    杀
    0.43
    Murder
    0.41
    ेंटल
    0.40
    POSITIVE LOGITS
     ashes
    0.44
     charred
    0.42
     cumpl
    0.41
     INFO
    0.40
     burnt
    0.39
     disintegrated
    0.39
     blackened
    0.38
     miserable
    0.38
     WORD
    0.38
    積分
    0.38
    Activations Density 0.006%

    No Known Activations