© 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. 47381
    Prev
    Next
    INDEX
    Explanations

    numbers and buying

    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
     yanı
    0.45
     պ
    0.42
     inclusivity
    0.42
     venezol
    0.42
    襁
    0.41
     τους
    0.40
     Maas
    0.40
    淒
    0.40
     outlier
    0.40
    ަނ
    0.39
    POSITIVE LOGITS
     ships
    0.42
     aastal
    0.42
     aircraft
    0.41
     figs
    0.41
     boats
    0.40
     sold
    0.40
    然后在
    0.40
    联合
    0.40
     garages
    0.40
     দত্ত
    0.39
    Activations Density 0.006%

    No Known Activations