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

    Neuronpedia

    Jacobian LensNEW
    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. 15128
    Prev
    Next
    INDEX
    Explanations

    Pride Month events

    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
    v
    0.87
     as
    0.66
     or
    0.66
     e
    0.64
    ")
    0.63
    一流
    0.57
    "))
    0.56
     می‌باشد
    0.55
     <
    0.55
    .",
    0.55
    POSITIVE LOGITS
     corrigir
    0.71
    ক্স
    0.68
    ଈ
    0.66
    দু
    0.62
    Après
    0.61
    Escape
    0.60
     sĩ
    0.60
     ಸಹಾಯ
    0.59
     mobilize
    0.59
    റ്റർ
    0.58
    Activations Density 0.001%

    No Known Activations