© 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-65K
    7. 36030
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or clauses

    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
     vede
    0.48
     á
    0.48
    굉
    0.48
     acción
    0.48
     Até
    0.47
     guardia
    0.47
    ії
    0.47
     Grecia
    0.47
    စွာ
    0.47
     esclus
    0.47
    POSITIVE LOGITS
    d
    0.57
    n
    0.55
    et
    0.54
    o
    0.52
    ER
    0.51
    Graph
    0.51
    Ingredient
    0.51
    Component
    0.50
    (
    0.50
    c
    0.49
    Activations Density 0.009%

    No Known Activations