© 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. 31-GEMMASCOPE-2-RES-65K
    7. 48658
    Prev
    Next
    INDEX
    Explanations

    tiennes, vraiment, aille, Louise

    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
    omás
    0.40
     cheats
    0.40
    躊
    0.40
     prin
    0.40
     preempt
    0.39
    碖
    0.39
     tersebut
    0.38
    遉
    0.38
     reconstructions
    0.37
    ដែរ
    0.37
    POSITIVE LOGITS
    J
    0.43
    èces
    0.41
    足够
    0.40
     Dino
    0.40
    受
    0.40
    gone
    0.39
    Harm
    0.38
    que
    0.38
    lire
    0.38
     বাহির
    0.37
    Activations Density 0.011%

    No Known Activations