© 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-16K
    7. 10628
    Prev
    Next
    INDEX
    Explanations

    following items

    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_16k_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
     त्यात
    0.39
     যের
    0.34
    鑣
    0.33
    一是
    0.33
     centaines
    0.33
     erfolgen
    0.33
     частина
    0.33
     केवळ
    0.33
    ivas
    0.32
    ()?;
    0.32
    POSITIVE LOGITS
     følgende
    1.78
     다음과
    1.77
     följande
    1.67
    以下の
    1.63
     following
    1.62
     folgender
    1.59
     निम्नलिखित
    1.59
    以下
    1.58
     folgende
    1.57
     নিম্নলিখিত
    1.57
    Activations Density 0.483%

    No Known Activations