© 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. 31-GEMMASCOPE-2-RES-262K
    4. 29367
    Prev
    Next
    INDEX
    Explanations

    Assigns/describes weights

    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
    ኰ
    0.50
     vreme
    0.49
    8
    0.47
     বৈশিষ্ট্য
    0.44
    ຮ
    0.44
    ਜ਼
    0.43
     veya
    0.43
    ClrType
    0.43
     පමණ
    0.42
     leto
    0.42
    POSITIVE LOGITS
    Cluster
    0.55
    "
    0.49
    According
    0.48
    Nuclear
    0.48
     Mixer
    0.48
    Na
    0.47
    Event
    0.47
    Software
    0.46
    AM
    0.46
     Notification
    0.45
    Activations Density 0.001%

    No Known Activations