Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84880
    Prev
    Next
    INDEX
    Explanations

    acts as an (emulsifier)

    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
     निकल
    0.44
     extruded
    0.44
     பாதுகா
    0.43
     cabello
    0.39
    ė
    0.39
     پا
    0.39
     خ
    0.39
     Stur
    0.39
    нул
    0.39
    ceded
    0.38
    POSITIVE LOGITS
    IAN
    0.43
    իմ
    0.41
    ייה
    0.41
     tragedies
    0.41
    מוד
    0.39
    śród
    0.38
    𝟘
    0.38
    വി
    0.38
    سے
    0.38
     জাতির
    0.38
    Activations Density 0.001%

    No Known Activations