© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11037
    Prev
    Next
    INDEX
    Explanations

    🇦🇺 flags and text in Japanese

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

    AI assistant identity

    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_40_width_16k_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
    /
    0.45
    ئے
    0.41
     ½
    0.40
    📝
    0.40
    𝙙
    0.40
     حر
    0.40
    °;
    0.40
     (;
    0.40
     centers
    0.39
     engines
    0.39
    POSITIVE LOGITS
    흠
    0.55
    앙
    0.51
    뜬
    0.44
    웬
    0.42
    푹
    0.42
    끈
    0.42
    ích
    0.42
    avant
    0.42
    챔
    0.41
    쏘
    0.41
    Activations Density 0.039%

    No Known Activations