© 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. 31-GEMMASCOPE-2-RES-262K
    7. 202910
    Prev
    Next
    INDEX
    Explanations

    intimacy and challenges

    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
    赤
    0.52
    วิ
    0.47
    ма
    0.44
    タ
    0.44
    ത
    0.43
    将
    0.43
     ви
    0.43
    над
    0.42
    Bar
    0.42
    Lai
    0.42
    POSITIVE LOGITS
     offsetting
    0.54
    🌯
    0.53
     indispensables
    0.50
     cargos
    0.48
     pigmentation
    0.48
     ਦਵਾਈ
    0.48
    timeStamp
    0.46
     OFFSET
    0.46
     nachos
    0.46
     fillers
    0.46
    Activations Density 0.001%

    No Known Activations