© 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. 43548
    Prev
    Next
    INDEX
    Explanations

    on followed by a topic

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

    Engagement signals and product interaction

    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
    壊
    0.42
    它是
    0.41
     ڈھ
    0.41
    宣言
    0.40
    下に
    0.39
    ک
    0.39
    そこに
    0.38
    遷移
    0.38
    انوں
    0.38
     aterriz
    0.38
    POSITIVE LOGITS
    两种
    0.43
     কিন্তু
    0.41
     হিন্দু
    0.41
     verschiedenen
    0.41
    ∑</
    0.40
    のですが
    0.39
     Hui
    0.38
     obce
    0.38
     видимо
    0.38
     enanti
    0.38
    Activations Density 0.000%

    No Known Activations