© 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. 53719
    Prev
    Next
    INDEX
    Explanations

    US and Ukraine collaborated

    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
    ERICK
    0.52
    <unused1071>
    0.48
    檗
    0.48
    樖
    0.48
    ণু
    0.48
    кте
    0.47
     QUILL
    0.46
     bhij
    0.46
    atorul
    0.46
    乀
    0.46
    POSITIVE LOGITS
    5
    0.52
    hed
    0.48
    tro
    0.45
    ties
    0.45
    marginal
    0.44
    3
    0.44
    ip
    0.44
     include
    0.43
    tv
    0.43
    s
    0.43
    Activations Density 0.023%

    No Known Activations