© 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. 39048
    Prev
    Next
    INDEX
    Explanations

    madame masterpiece tragedy monsieur

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

    perceived moral situation

    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
     warmup
    0.46
     direc
    0.45
     directorio
    0.41
    еха
    0.39
    ANT
    0.39
     directs
    0.38
     marries
    0.38
    쫙
    0.38
     contrib
    0.38
     fiercely
    0.38
    POSITIVE LOGITS
    那位
    0.46
     manusia
    0.45
     masterpiece
    0.45
    這位
    0.40
     madame
    0.40
    ╯
    0.40
    ْت
    0.40
     tragedy
    0.39
     एखा
    0.39
     संसार
    0.39
    Activations Density 0.000%

    No Known Activations