© 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-65K
    4. 3182
    Prev
    Next
    INDEX
    Explanations

    what if

    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
     антен
    0.56
    楽曲
    0.56
    銨
    0.55
    髖
    0.54
    鈦
    0.52
    جموعة
    0.50
    音频
    0.50
    鸬
    0.50
     гли
    0.50
    齦
    0.50
    POSITIVE LOGITS
    ji
    0.62
     stupid
    0.62
     unbearable
    0.61
     domine
    0.61
     pitiful
    0.59
     Xia
    0.58
    ut
    0.58
    je
    0.58
     Jia
    0.56
     helplessly
    0.56
    Activations Density 0.016%

    No Known Activations