© 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. 17882
    Prev
    Next
    INDEX
    Explanations

    `=` and `toEqual` in code

    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
     aggrav
    0.82
     ер
    0.79
     splashes
    0.72
     ε
    0.68
     кон
    0.66
     scallops
    0.66
     кос
    0.66
     س
    0.64
     გამ
    0.64
     ако
    0.63
    POSITIVE LOGITS
    ने
    0.97
    오
    0.93
    त
    0.93
    ad
    0.89
    મ
    0.89
    и
    0.88
    어
    0.87
    ar
    0.79
    ó
    0.79
    미
    0.78
    Activations Density 0.000%

    No Known Activations