© 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. 31613
    Prev
    Next
    INDEX
    Explanations

    cursor, border, text

    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
    padding
    0.47
     padding
    0.42
     preimage
    0.38
    ULONG
    0.36
     ヨ
    0.36
    実際
    0.36
     ปุ่ม
    0.35
     مجموعه
    0.34
     suốt
    0.34
    蔷
    0.34
    POSITIVE LOGITS
    cursor
    0.58
     cursor
    0.55
    Cursor
    0.50
     Acceler
    0.39
    cur
    0.38
    Cur
    0.38
    user
    0.37
    vel
    0.36
    っかけ
    0.36
    CASE
    0.36
    Activations Density 0.012%

    No Known Activations