© 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. 6245
    Prev
    Next
    INDEX
    Explanations

    recursive function calls and conditions

    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
     degust
    0.43
    že
    0.41
     Sanct
    0.41
    revoke
    0.41
    affaires
    0.39
     свят
    0.39
    ைச்
    0.39
    ގ
    0.39
    poems
    0.38
    นม
    0.38
    POSITIVE LOGITS
     recursively
    0.90
     recursive
    0.81
     recursion
    0.79
    Recursive
    0.72
    递归
    0.70
     Recurs
    0.70
     Recursive
    0.69
     partitioning
    0.68
    recursive
    0.65
    Recurs
    0.64
    Activations Density 0.171%

    No Known Activations