© 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. 20662
    Prev
    Next
    INDEX
    Explanations

    end of phrase or question

    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
    Kuota
    0.38
    tracked
    0.36
     sourceL
    0.36
    AxisSize
    0.35
    सा
    0.35
    ன்னி
    0.35
    Viet
    0.34
    翛
    0.34
    ன்ன
    0.34
    ﺎ
    0.34
    POSITIVE LOGITS
     irritability
    0.40
    ﹑
    0.38
     ஏற்படுத்து
    0.37
     또는
    0.37
     &/
    0.37
     போன்றவற்ற
    0.37
     Cleveland
    0.36
    及び
    0.35
    もしくは
    0.35
    lblName
    0.34
    Activations Density 0.137%

    No Known Activations