© 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. 144440
    Prev
    Next
    INDEX
    Explanations

    multilingual simplicity and rules

    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
    fromi
    0.58
    倸
    0.55
     Vegetation
    0.54
     المللی
    0.52
     इनटू
    0.51
     organiques
    0.51
     말미암아
    0.51
    ₁.
    0.50
    
    0.49
     Utilizing
    0.49
    POSITIVE LOGITS
     hospital
    0.46
    Hospital
    0.45
     township
    0.45
     village
    0.44
     simple
    0.43
     survey
    0.43
     regard
    0.42
    Hoff
    0.42
    て
    0.41
     investigating
    0.40
    Activations Density 0.000%

    No Known Activations