© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57013
    Prev
    Next
    INDEX
    Explanations

    keys, offensive, labor

    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
     เพิ่ม
    0.61
     aby
    0.48
     ทั้ง
    0.48
     elér
    0.46
    शिला
    0.46
     他
    0.45
     بهبود
    0.45
     habl
    0.45
     பயிற்சிய
    0.44
     모집
    0.43
    POSITIVE LOGITS
    odium
    0.51
    {
    0.45
    bright
    0.44
    白色
    0.42
    ოველ
    0.42
    қ
    0.42
    Compute
    0.42
    define
    0.42
    unique
    0.41
    íu
    0.41
    Activations Density 0.001%

    No Known Activations