© 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. 10879
    Prev
    Next
    INDEX
    Explanations

    merely, only, just

    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
     unrestricted
    0.42
    жа
    0.38
    क्सी
    0.38
     때문
    0.38
     ஒன்றாகும்
    0.38
    ั้ง
    0.37
     ફરી
    0.37
    乂
    0.37
    central
    0.36
     spontaneously
    0.36
    POSITIVE LOGITS
    只是
    1.12
     merely
    1.11
     lediglich
    1.04
     jedynie
    0.96
     केवल
    0.85
     лишь
    0.84
     chỉ
    0.80
     sadece
    0.79
     only
    0.78
     apenas
    0.78
    Activations Density 0.493%

    No Known Activations