© 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. 141086
    Prev
    Next
    INDEX
    Explanations

    加 / add / 加上

    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
     have
    0.74
    ו
    0.65
    to
    0.61
    мимо
    0.61
     dilwale
    0.59
    hwar
    0.59
    have
    0.58
     intimidate
    0.57
    들이
    0.56
     interchange
    0.56
    POSITIVE LOGITS
    加
    0.79
    eres
    0.65
    ators
    0.64
     ويمكن
    0.62
    ins
    0.61
    লিখিত
    0.60
    起来
    0.59
    ر
    0.59
    enden
    0.58
    unas
    0.58
    Activations Density 0.001%

    No Known Activations