© 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. 65359
    Prev
    Next
    INDEX
    Explanations

    political topics, names or labels

    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
    Racing
    0.40
    }\
    0.39
     ری
    0.39
    )\
    0.38
    りが
    0.38
    的过程中
    0.38
     INTRODUCTION
    0.37
    畅
    0.37
     quotid
    0.36
     vocational
    0.36
    POSITIVE LOGITS
    gelijk
    0.46
     toga
    0.44
     llamas
    0.44
     Dutton
    0.44
    kiye
    0.43
    oughton
    0.43
     Arroyo
    0.43
    عون
    0.43
    níky
    0.43
     toilets
    0.42
    Activations Density 0.003%

    No Known Activations