© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 2225
    Prev
    Next
    INDEX
    Explanations

    Joe Biden as president

    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_16_width_262k_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
     細胞
    0.31
    𝙜
    0.30
    𝐠
    0.29
    ﺍ
    0.29
    這個
    0.27
    𒊒
    0.27
     様
    0.27
    𝐟
    0.27
     доступа
    0.27
     لهذا
    0.27
    POSITIVE LOGITS
     Biden
    0.32
    Biden
    0.29
    re
    0.26
    in
    0.25
     exiting
    0.24
     incentivize
    0.24
     Putin
    0.23
    ин
    0.23
     ক্ষমতায়
    0.23
     signaling
    0.23
    Activations Density 0.019%

    No Known Activations