© 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. 56060
    Prev
    Next
    INDEX
    Explanations

    when something started

    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
     DS
    0.46
     EW
    0.43
     building
    0.43
     manufacturer
    0.43
     illustrating
    0.42
    EW
    0.41
     CF
    0.41
    誘
    0.41
    DS
    0.41
     GT
    0.40
    POSITIVE LOGITS
    之时
    0.47
    
    0.47
    之际
    0.44
    ):=\
    0.43
    刘
    0.43
    یدن
    0.43
     ediyorum
    0.43
    閡
    0.43
    蠵
    0.42
     Halt
    0.42
    Activations Density 0.006%

    No Known Activations