© 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-16K
    7. 11706
    Prev
    Next
    INDEX
    Explanations

    labels and questions

    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_16k_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
     P
    0.51
     crim
    0.47
     criminally
    0.46
    con
    0.43
    ,
    0.43
     as
    0.42
     over
    0.42
     g
    0.42
     crime
    0.42
     criminal
    0.41
    POSITIVE LOGITS
    irrahim
    0.50
    溘
    0.50
     وهذه
    0.48
    睄
    0.45
     yanlı
    0.41
    యో
    0.41
    ума
    0.41
    ванию
    0.41
    暐
    0.41
     இவை
    0.40
    Activations Density 0.004%

    No Known Activations