© 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. 16-GEMMASCOPE-2-RES-262K
    7. 11782
    Prev
    Next
    INDEX
    Explanations

    awful, terribly, dreadfully

    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_16_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
    т
    1.16
     It
    1.02
    ม
    1.00
    ر
    0.96
     A
    0.92
     Several
    0.91
     respectivos
    0.91
    к
    0.91
     I
    0.89
     Okinawa
    0.88
    POSITIVE LOGITS
    لي
    1.10
    aire
    0.99
    ası
    0.96
    6
    0.95
    ani
    0.90
    p
    0.89
    ında
    0.88
     রকমের
    0.87
    um
    0.86
    ane
    0.86
    Activations Density 0.011%

    No Known Activations