© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1262
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite

    bubbling up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ed
    0.47
    able
    0.41
     functioning
    0.40
    functioning
    0.39
    ের
    0.39
    ल
    0.39
    ی
    0.38
    s
    0.38
     funcionando
    0.37
     lacking
    0.36
    POSITIVE LOGITS
    ly
    0.58
      
    0.45
    redients
    0.43
    gggg
    0.42
     oneself
    0.40
    ness
    0.38
     intently
    0.36
    ggg
    0.35
    too
    0.33
     purposes
    0.33
    Activations Density 1.227%

    No Known Activations