© 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-16K
    7. 1091
    Prev
    Next
    INDEX
    Explanations

    required or optional arguments

    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_16k_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
     combatir
    0.41
     paralysie
    0.41
     পরাজ
    0.39
    妻子
    0.39
    äst
    0.38
    泡
    0.38
     entrev
    0.38
    瞑
    0.38
     photosynthesis
    0.38
     vườn
    0.37
    POSITIVE LOGITS
     optional
    0.66
    required
    0.64
     required
    0.63
     usually
    0.60
     Optional
    0.60
    不能为空
    0.60
     mandatory
    0.57
     Required
    0.57
    REQUIRED
    0.56
     REQUIRED
    0.56
    Activations Density 0.847%

    No Known Activations