© 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. 47565
    Prev
    Next
    INDEX
    Explanations

    watermark

    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
     omkring
    0.70
     বিজ্ঞানী
    0.70
     bạn
    0.68
    कल
    0.66
    🍲
    0.66
     simulating
    0.64
     lidt
    0.64
     cepat
    0.63
    เกม
    0.63
     waahanga
    0.63
    POSITIVE LOGITS
    0.66
    وية
    0.62
     watermark
    0.61
    تما
    0.60
     U
    0.59
    overlay
    0.59
    positions
    0.59
    VB
    0.58
    rho
    0.58
    MaxSize
    0.57
    Activations Density 0.006%

    No Known Activations