© 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. 4715
    Prev
    Next
    INDEX
    Explanations

    advice and communication

    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
    喈
    0.50
    乸
    0.49
    瑷
    0.48
    摀
    0.48
    からも
    0.47
    硖
    0.47
     хирур
    0.47
     våra
    0.45
    紵
    0.45
    лянчук
    0.44
    POSITIVE LOGITS
    ，
    0.63
     diferentes
    0.62
     exquisite
    0.59
    ；
    0.59
    的
    0.56
    和
    0.56
    不同的
    0.55
     مختلفة
    0.54
     despicable
    0.52
    、
    0.52
    Activations Density 0.041%

    No Known Activations