© 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. 17793
    Prev
    Next
    INDEX
    Explanations

    a deep dive

    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
    ik
    1.15
    t
    1.10
    _
    1.09
    ana
    0.97
    ol
    0.95
    ok
    0.93
    m
    0.88
    ing
    0.88
    ir
    0.88
    ore
    0.84
    POSITIVE LOGITS
     consciente
    0.91
     effectués
    0.88
     nguyện
    0.87
     effectuées
    0.84
     لیګ
    0.82
    تي
    0.81
     бе
    0.80
     innych
    0.79
    𝟖
    0.78
     продуктов
    0.78
    Activations Density 0.255%

    No Known Activations