© 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-262K
    7. 6180
    Prev
    Next
    INDEX
    Explanations

    contextual prepositions

    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_262k_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
     sterile
    0.52
     tier
    0.50
     handy
    0.50
     Beckham
    0.48
    ’
    0.47
     coffers
    0.47
     weakens
    0.46
     oiled
    0.46
     triglycerides
    0.46
     gallon
    0.46
    POSITIVE LOGITS
    表达
    0.53
    l
    0.52
    ligare
    0.49
    令人
    0.47
    记载
    0.47
     hodnot
    0.46
    倾向
    0.46
    勉
    0.44
    机会
    0.44
    盼
    0.44
    Activations Density 0.000%

    No Known Activations