© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 18395
    Prev
    Next
    INDEX
    Explanations

    On discussing academic subjects

    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
     डिपार्टमेंट
    0.62
    rient
    0.59
    ر
    0.57
    ौरा
    0.55
    emorrh
    0.55
    <0xAC>
    0.54
    --->
    0.53
    quered
    0.53
    ంచరీలు
    0.53
    д
    0.52
    POSITIVE LOGITS
     LL
    0.62
    ের
    0.61
     GDP
    0.60
    n
    0.60
     SSH
    0.58
     HPC
    0.58
     ESG
    0.57
     SS
    0.57
     SSD
    0.57
     protégé
    0.56
    Activations Density 0.000%

    No Known Activations