© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4116
    Prev
    Next
    INDEX
    Explanations

    Sichuan, Shichen, Wuren, Guo Tai Ming

    np_acts-logits-general · gemini-2.5-flash-lite

    灵灵隐丁义尖峰豚カツ景城夕力断桥尊者白药

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    銠
    0.44
    鸬
    0.42
    鈮
    0.41
    鈽
    0.41
    நீங்கள்
    0.40
    齙
    0.40
    鉭
    0.40
     рэгістрацыі
    0.40
    𝖺
    0.39
    馇
    0.39
    POSITIVE LOGITS
    々
    0.37
    士
    0.35
    T
    0.35
    ch
    0.34
    0.34
    Y
    0.33
     un
    0.33
    G
    0.33
    理
    0.33
    道
    0.33
    Activations Density 0.062%

    No Known Activations