© 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-65K
    7. 11489
    Prev
    Next
    INDEX
    Explanations

    simplifying complex logic

    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
     ткани
    0.48
    𒁀
    0.46
    stoffen
    0.44
     그녀
    0.43
    氇
    0.43
     খাতে
    0.43
    ،
    0.43
    痠
    0.43
     fabrics
    0.42
    onesia
    0.42
    POSITIVE LOGITS
     simplified
    0.57
     simplification
    0.52
     simplify
    0.50
     reduced
    0.49
    T
    0.47
    on
    0.47
     Simplify
    0.47
    reduced
    0.47
     redução
    0.47
    simplified
    0.47
    Activations Density 0.002%

    No Known Activations