© 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. 55511
    Prev
    Next
    INDEX
    Explanations

    technical explanation

    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
    bin
    0.45
    iris
    0.45
    bibitem
    0.43
    allenges
    0.42
    {\'
    0.42
    alleng
    0.42
    ogran
    0.41
    logn
    0.41
    mlin
    0.40
     replete
    0.40
    POSITIVE LOGITS
     내부
    0.55
     능력
    0.52
    ن
    0.49
     что
    0.48
    연구
    0.48
    ат
    0.48
     Çünkü
    0.48
    工业
    0.47
    一个
    0.47
     由
    0.46
    Activations Density 0.007%

    No Known Activations