© 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. 111322
    Prev
    Next
    INDEX
    Explanations

    meta-ethics and moral subjectivity

    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
     философ
    0.49
    Princ
    0.44
     принци
    0.42
    亅
    0.40
    CurrentImageData
    0.39
    丅
    0.39
    枥
    0.39
    дзі
    0.38
    艋
    0.38
    𐰴
    0.38
    POSITIVE LOGITS
     Natural
    0.44
     Mackie
    0.43
     meta
    0.43
     Meta
    0.42
     Hume
    0.42
    meta
    0.40
     Horm
    0.40
     NATURAL
    0.39
     natural
    0.38
     Evolutionary
    0.38
    Activations Density 0.022%

    No Known Activations