© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134051
    Prev
    Next
    INDEX
    Explanations

    uncover your passions

    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
    dataFormat
    0.46
     deformation
    0.42
     بنا
    0.42
     turner
    0.41
     invisibility
    0.40
    ◸
    0.40
     scaleOf
    0.40
     वेगवेग
    0.39
    াদা
    0.38
     मिश्रण
    0.38
    POSITIVE LOGITS
    起動
    0.37
    კ
    0.37
    今年も
    0.37
    sel
    0.36
    ដ
    0.36
    ค
    0.35
    ritis
    0.35
     th
    0.35
    含む
    0.35
    を開
    0.34
    Activations Density 0.000%

    No Known Activations