© 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. 50169
    Prev
    Next
    INDEX
    Explanations

    URLs and domain names

    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
     ንጥረ
    0.27
     상세
    0.24
     機械
    0.23
     അള
    0.23
     значений
    0.23
     웹
    0.22
     файлов
    0.22
     რომელი
    0.21
     വിദ
    0.21
     過
    0.21
    POSITIVE LOGITS
     tributes
    0.24
     evento
    0.24
     Ministers
    0.24
    lections
    0.23
     भाजपा
    0.23
     Congressman
    0.22
    iran
    0.22
    President
    0.22
     Minister
    0.22
     pamphlets
    0.22
    Activations Density 0.001%

    No Known Activations