© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 109557
    Prev
    Next
    INDEX
    Explanations

    bowing or kneeling

    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
     comando
    0.51
    指令
    0.46
    コマンド
    0.45
     명령어
    0.44
     comandos
    0.42
     instructing
    0.41
    𒂵
    0.40
    バンド
    0.40
    SSL
    0.40
     इंटरेस्ट
    0.40
    POSITIVE LOGITS
     respectfully
    0.81
     respectful
    0.79
     loyalty
    0.73
     dutiful
    0.71
    谄
    0.71
     obedience
    0.70
     Loyalty
    0.70
     loy
    0.68
     subserv
    0.65
    跪
    0.65
    Activations Density 0.024%

    No Known Activations