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

    Neuronpedia

    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. 40229
    Prev
    Next
    INDEX
    Explanations

    buckling behavior

    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
    for
    0.61
    the
    0.60
    )*(
    0.54
     abnormalities
    0.52
     the
    0.52
     restrictions
    0.49
    f
    0.49
     understand
    0.49
     and
    0.48
     funding
    0.48
    POSITIVE LOGITS
     bicovariant
    0.56
     从
    0.52
     गर्भावस्था
    0.52
    ведение
    0.52
     装
    0.51
     لینا
    0.50
    üler
    0.50
     ભાગ
    0.49
     类
    0.49
     terapé
    0.49
    Activations Density 0.000%

    No Known Activations