© 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-65K
    7. 47375
    Prev
    Next
    INDEX
    Explanations

    riddles with 'wet' outcomes

    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_65k_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
    受
    0.49
     Yuri
    0.47
     mycket
    0.47
     lucrative
    0.45
     accrued
    0.45
     playoffs
    0.45
     Y
    0.45
    0.44
     aggrieved
    0.44
     overpowered
    0.43
    POSITIVE LOGITS
    у
    0.57
    Furniture
    0.55
     мебели
    0.55
    Бар
    0.54
    ро
    0.54
    መሪያ
    0.52
    furniture
    0.52
    的关键
    0.50
    的他
    0.50
    款式
    0.50
    Activations Density 0.009%

    No Known Activations