© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6751
    Prev
    Next
    INDEX
    Explanations

    living in, with, through, or like

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

    living

    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
    verläss
    0.40
    consolid
    0.39
    频
    0.39
     Verwaltung
    0.39
    randomIndex
    0.38
     MeV
    0.37
    lässlich
    0.37
    ുകാര
    0.37
    ępnie
    0.37
    巩
    0.36
    POSITIVE LOGITS
     жизнью
    0.67
     vidas
    0.66
     حياة
    0.65
     lives
    0.63
     paycheck
    0.60
     rent
    0.60
     frug
    0.60
     vic
    0.59
     happily
    0.58
     frugal
    0.58
    Activations Density 0.078%

    No Known Activations