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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 103507
    Prev
    Next
    INDEX
    Explanations

    network infrastructure

    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
    у
    1.06
    م
    0.97
    ع
    0.95
    ب
    0.93
    ম
    0.91
    म
    0.90
    ти
    0.89
    ab
    0.88
    for
    0.88
    न
    0.87
    POSITIVE LOGITS
     bracelet
    0.68
     is
    0.66
    </h6>
    0.65
    </h1>
    0.63
    的消息
    0.63
    </h2>
    0.63
     terület
    0.63
     lidí
    0.61
     whiskey
    0.61
    </u>
    0.60
    Activations Density 0.000%

    No Known Activations