© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 2033
    Prev
    Next
    INDEX
    Explanations

    translate, summarize, documentation, debugging, troubleshooting

    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_262k_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
    Е
    0.48
     계산
    0.45
     Рі
    0.42
     outraged
    0.39
    숫
    0.39
    ե
    0.39
     Е
    0.38
     blatantly
    0.38
    俱乐
    0.38
    
    0.37
    POSITIVE LOGITS
     và
    0.55
     inoltre
    0.55
     też
    0.50
     Außerdem
    0.50
     மற்றும்
    0.49
     以及
    0.48
     and
    0.47
     etc
    0.47
    以及
    0.47
     serta
    0.47
    Activations Density 0.173%

    No Known Activations