© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6462
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases and conjunctions

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

    Southern Poverty

    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
     gleaned
    0.51
     मसलन
    0.49
    xxx
    0.48
     esche
    0.47
     करीत
    0.46
    Incidentally
    0.46
     ं
    0.44
     ostensibly
    0.43
     bemo
    0.43
     preponder
    0.43
    POSITIVE LOGITS
     idk
    0.71
     lmao
    0.61
     वीडियोस
    0.61
     beforehand
    0.59
    😶
    0.58
     alot
    0.56
    🗿
    0.56
     चीज़
    0.55
    🌚
    0.54
     ©️
    0.53
    Activations Density 0.223%

    No Known Activations