© 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. 47602
    Prev
    Next
    INDEX
    Explanations

    in ghostly spaces

    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
     resorting
    0.45
     coastline
    0.44
     investigating
    0.43
     outside
    0.43
     boardwalk
    0.43
    Ꮲ
    0.43
    debugging
    0.42
     using
    0.41
     साल
    0.41
     immunology
    0.40
    POSITIVE LOGITS
     ока
    0.45
     θέση
    0.43
     Pocket
    0.41
     crevices
    0.41
     pudd
    0.41
    ช่อง
    0.41
     Slot
    0.40
    侾
    0.40
     Рэ
    0.40
     отверсти
    0.40
    Activations Density 0.064%

    No Known Activations