© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49492
    Prev
    Next
    INDEX
    Explanations

    steal from

    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
    ي
    0.97
    蜓
    0.89
    '{
    0.85
    но
    0.80
    י
    0.80
    ד
    0.79
     luscious
    0.77
    ni
    0.75
    అ
    0.75
    ggi
    0.75
    POSITIVE LOGITS
    לות
    1.05
    ers
    0.97
    have
    0.95
    <0x0D>
    0.93
    ва
    0.93
    ر
    0.90
    לב
    0.88
    었다
    0.85
    لها
    0.81
    ل
    0.80
    Activations Density 0.004%

    No Known Activations