© 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. 6222
    Prev
    Next
    INDEX
    Explanations

    intending to do

    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
    䈉
    0.25
    然後
    0.25
    多い
    0.24
     indicó
    0.24
     usamos
    0.24
    एक
    0.24
    કો
    0.24
     it
    0.23
    غر
    0.23
    壃
    0.23
    POSITIVE LOGITS
     to
    0.32
     قادر
    0.24
     deactivate
    0.24
    ุ
    0.24
    Liz
    0.24
    to
    0.23
     improve
    0.23
     save
    0.22
     maintain
    0.21
    Dok
    0.21
    Activations Density 0.150%

    No Known Activations