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

    Neuronpedia

    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. 138539
    Prev
    Next
    INDEX
    Explanations

    foreign ministers, comforta, numbs

    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
    យៈ
    0.55
    ᇁ
    0.53
    欳
    0.51
    MPT
    0.51
    ୟ
    0.51
     поверну
    0.50
    ナソニック
    0.48
    ᆭ
    0.47
    పథ
    0.46
     вероят
    0.46
    POSITIVE LOGITS
     Bur
    0.61
     oil
    0.57
    um
    0.57
     OSS
    0.54
     Oil
    0.54
    ite
    0.50
    )
    0.50
     ombil
    0.50
    .
    0.50
     Stock
    0.48
    Activations Density 0.000%

    No Known Activations