© 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. 31-GEMMASCOPE-2-RES-262K
    7. 128378
    Prev
    Next
    INDEX
    Explanations

    float or extraordinary prop

    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_31_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
     ascii
    0.41
    Americans
    0.40
    Introdu
    0.39
    面积
    0.39
     হচ্ছেন
    0.38
     گویا
    0.38
     cytos
    0.37
    剧
    0.37
    textrm
    0.36
     introduction
    0.36
    POSITIVE LOGITS
     Dividend
    0.51
    <unused37>
    0.49
     liquidated
    0.49
     عند
    0.48
     pensions
    0.48
     कपकेक
    0.47
    憫
    0.47
     recoup
    0.47
     refunded
    0.47
    unsplash
    0.46
    Activations Density 0.001%

    No Known Activations