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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84717
    Prev
    Next
    INDEX
    Explanations

    advance directives, chapters, empathy, ideas

    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
     diffusion
    0.50
     difusión
    0.46
    젖
    0.42
     dyeing
    0.42
    曼
    0.40
    diffusion
    0.40
     television
    0.40
     washing
    0.39
     Washing
    0.39
     DVD
    0.39
    POSITIVE LOGITS
     ഉറ
    0.55
    🕊
    0.50
    കേന്ദ്രം
    0.47
     እንቅ
    0.47
     поги
    0.46
    astopol
    0.46
     พิจิก
    0.46
    vrdr
    0.45
    και
    0.45
    持つ
    0.45
    Activations Density 0.002%

    No Known Activations