© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9586
    Prev
    Next
    INDEX
    Explanations

    to or Toledo

    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
    ни
    0.82
    ים
    0.71
    ের
    0.69
    ു
    0.66
    inare
    0.61
     mojo
    0.58
    tiger
    0.57
    িত
    0.56
    τρο
    0.55
    tumor
    0.54
    POSITIVE LOGITS
    어
    0.92
    新
    0.89
    การ
    0.81
     сообщи
    0.76
    กำลัง
    0.74
    م
    0.70
    Bl
    0.69
    กล
    0.68
    C
    0.68
    Tos
    0.67
    Activations Density 0.059%

    No Known Activations