© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92435
    Prev
    Next
    INDEX
    Explanations

    describing processes or states

    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
    کت
    0.48
     시스템
    0.47
     failures
    0.46
     엔
    0.44
     रिपोर्ट्स
    0.44
     usuarios
    0.44
    的方法
    0.42
    貌
    0.42
     системе
    0.41
     agonists
    0.41
    POSITIVE LOGITS
     decreasing
    0.51
     æ
    0.46
     會
    0.46
    الج
    0.46
     Long
    0.46
    decreasing
    0.45
     lavender
    0.45
    ã
    0.44
     Lavender
    0.43
    on
    0.43
    Activations Density 0.002%

    No Known Activations