© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51413
    Prev
    Next
    INDEX
    Explanations

    Mixture of Experts (MoE)

    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
     obstacles
    0.54
     dismay
    0.52
     awarding
    0.51
     inferences
    0.48
    ।
    0.48
     วิ
    0.47
     asymmetries
    0.47
     buty
    0.46
     비
    0.46
    绚
    0.45
    POSITIVE LOGITS
    }$).
    0.52
    daq
    0.49
    櫒
    0.48
    jmp
    0.46
    нда
    0.44
    اخ
    0.44
    ور
    0.42
    تاة
    0.42
    奔
    0.42
    }<\
    0.41
    Activations Density 0.002%

    No Known Activations