© 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. 31529
    Prev
    Next
    INDEX
    Explanations

    medical conditions and diseases

    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
     reméd
    0.71
     что
    0.68
    𝕒
    0.64
    ଐ
    0.64
    𝕕
    0.64
     மருத்து
    0.63
    増加
    0.62
    ahuje
    0.62
     férias
    0.62
     пациентов
    0.61
    POSITIVE LOGITS
    b
    0.88
    j
    0.83
    ed
    0.80
    z
    0.79
    re
    0.78
    ek
    0.77
    of
    0.77
    www
    0.72
    '
    0.71
    but
    0.66
    Activations Density 0.008%

    No Known Activations