© 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. 31-GEMMASCOPE-2-RES-65K
    7. 51127
    Prev
    Next
    INDEX
    Explanations

    fantasy rpgs and lore

    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_31_width_65k_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
     polisi
    0.58
     mamá
    0.57
    離婚
    0.57
     엄마
    0.52
    苺
    0.52
     মিসেস
    0.52
     papá
    0.52
    公寓
    0.51
    媽媽
    0.50
     superheroes
    0.50
    POSITIVE LOGITS
     Skyrim
    0.73
     runes
    0.67
     parchment
    0.66
    ⚔
    0.65
     древ
    0.64
     Warhammer
    0.64
     Tolkien
    0.59
     ancient
    0.59
     sword
    0.59
     medieval
    0.59
    Activations Density 0.375%

    No Known Activations