© 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. 82543
    Prev
    Next
    INDEX
    Explanations

    high and low frequencies and speeds

    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
    鞅
    0.46
    帮忙
    0.43
    pperware
    0.43
    坞
    0.42
    ᴼ
    0.41
     सौभाग्य
    0.41
    arantee
    0.41
    Ellipse
    0.41
     বিলম্ব
    0.40
    Demo
    0.40
    POSITIVE LOGITS
     beyond
    0.62
     (>
    0.57
    beyond
    0.56
     (<
    0.54
     rar
    0.49
     $(<
    0.47
     Beyond
    0.47
    ≳
    0.46
    near
    0.46
     nearing
    0.45
    Activations Density 0.114%

    No Known Activations