© 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-262K
    7. 50982
    Prev
    Next
    INDEX
    Explanations

    decoded string or text

    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
    𝗯
    0.50
    𝗧
    0.50
     باس
    0.46
     сорта
    0.46
    𝐓
    0.46
     বীজ
    0.45
     ವಿವಿಧ
    0.45
     ס
    0.44
     начну
    0.44
    zeug
    0.44
    POSITIVE LOGITS
    议
    0.44
    宜
    0.43
     phone
    0.43
    正确
    0.42
     June
    0.42
    ദ്
    0.42
    删除
    0.42
    å
    0.42
    溅
    0.42
    经
    0.42
    Activations Density 0.002%

    No Known Activations