© 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. 169605
    Prev
    Next
    INDEX
    Explanations

    history entered by Dealer

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

    monitoring, Max, safe, heavily

    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
    ad
    0.43
    篇文章
    0.40
     ad
    0.40
     possibilità
    0.40
    頻
    0.39
    rel
    0.38
    記事
    0.38
    SSR
    0.38
    1
    0.38
    粘
    0.38
    POSITIVE LOGITS
    මණ
    0.50
    ि
    0.50
     আনুষ্ঠানিকভাবে
    0.48
    ቿ
    0.48
     मात्र
    0.48
     безу
    0.47
    𝚎
    0.47
    ത്വം
    0.46
    া
    0.46
    কিন্ত
    0.46
    Activations Density 0.001%

    No Known Activations