© 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. 31-GEMMASCOPE-2-RES-262K
    7. 202610
    Prev
    Next
    INDEX
    Explanations

    square brackets list

    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_31_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
     улы
    0.47
    ᅭ
    0.45
    Coca
    0.43
     plummeted
    0.43
     государство
    0.43
     стр
    0.42
    prés
    0.41
     plummet
    0.41
    ྦ
    0.41
     たり
    0.41
    POSITIVE LOGITS
    一条
    0.54
    电
    0.53
    讲述
    0.50
    但
    0.50
    一套
    0.48
    文化
    0.48
    大
    0.48
    美国
    0.48
    δη
    0.46
    程序
    0.46
    Activations Density 0.002%

    No Known Activations