© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167552
    Prev
    Next
    INDEX
    Explanations

    year descriptions

    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_40_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
    ggbb
    0.42
    那时
    0.40
    籠
    0.40
    笼
    0.39
    頃
    0.39
     calorimetry
    0.39
    DefaultFor
    0.38
    薰
    0.38
    thickmathspace
    0.37
     आढा
    0.37
    POSITIVE LOGITS
     year
    0.78
    year
    0.71
     рік
    0.67
     yılı
    0.66
     jaar
    0.66
     Jahr
    0.64
     année
    0.62
     год
    0.61
     godina
    0.61
     साल
    0.61
    Activations Density 0.023%

    No Known Activations