© 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. 30882
    Prev
    Next
    INDEX
    Explanations

    per basis

    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
     it
    1.06
     {
    1.06
     by
    1.03
     been
    0.88
    ht
    0.83
    ได้
    0.82
    ering
    0.80
     ت
    0.80
     was
    0.79
    ：
    0.79
    POSITIVE LOGITS
    не
    1.29
    u
    1.10
    지
    1.05
    ين
    1.04
    ق
    1.04
    ع
    1.02
    ме
    1.00
    v
    0.96
    ко
    0.94
    לי
    0.93
    Activations Density 0.000%

    No Known Activations