© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37561
    Prev
    Next
    INDEX
    Explanations

    Moral accountability; sin and consequence

    np_acts-logits-general · gemini-2.5-flash-lite

    Utilitarianism and '-ism' words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quela
    0.48
     mortals
    0.47
    ↵
    0.47
    quele
    0.47
    記載
    0.41
     lokalen
    0.41
     hiszen
    0.41
     sehingga
    0.39
     demandas
    0.38
     चुनौतियों
    0.38
    POSITIVE LOGITS
    е
    0.48
     শব্দের
    0.46
     หรือ
    0.46
    ัพท์
    0.46
    īt
    0.45
    "="
    0.45
    的东西
    0.45
    镞
    0.44
    ကြောင့်
    0.43
    หรือ
    0.43
    Activations Density 0.000%

    No Known Activations