© 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. 76435
    Prev
    Next
    INDEX
    Explanations

    defining and clarifying terms

    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
    与
    0.45
    缺
    0.45
     ተጨማሪ
    0.44
     pollute
    0.44
    不要
    0.44
     đột
    0.44
     suspicious
    0.43
    这就是
    0.43
    E
    0.43
    ktr
    0.43
    POSITIVE LOGITS
     gente
    0.47
     aficionados
    0.46
     organismos
    0.46
     chale
    0.46
     REPORTS
    0.45
    נים
    0.44
     Jobs
    0.44
     episodios
    0.43
     eccles
    0.43
     atas
    0.42
    Activations Density 0.002%

    No Known Activations