© 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. 31-GEMMASCOPE-2-RES-262K
    7. 94008
    Prev
    Next
    INDEX
    Explanations

    primarily targeting

    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
     ダン
    0.50
    트
    0.49
    ر
    0.48
    ">{{
    0.46
    adine
    0.45
    icur
    0.44
     Arc
    0.43
    ートン
    0.42
     mon
    0.42
    મત
    0.42
    POSITIVE LOGITS
    caused
    0.41
     CHCl
    0.41
    手续
    0.41
    answers
    0.40
     চক্ষ
    0.39
     systeem
    0.39
    漏
    0.38
     অধিদপ্তর
    0.38
     системы
    0.37
     ماہر
    0.37
    Activations Density 0.003%

    No Known Activations