© 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. 53-GEMMASCOPE-2-RES-262K
    7. 9098
    Prev
    Next
    INDEX
    Explanations

    liquids dripping and spilling

    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_53_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
     قبض
    0.41
     божомол
    0.36
    排序
    0.36
     сорти
    0.36
    伐
    0.36
    膂
    0.36
     Crusade
    0.35
    ঠি
    0.35
     నిషే
    0.35
    ̉i
    0.34
    POSITIVE LOGITS
     drips
    1.98
     dripping
    1.86
     drip
    1.73
     droplets
    1.65
    滴
    1.60
     pudd
    1.47
     puddle
    1.45
     dri
    1.34
     spills
    1.34
     drib
    1.33
    Activations Density 0.066%

    No Known Activations