© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17277
    Prev
    Next
    INDEX
    Explanations

    residing, dwelling, living

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

    sorghum granola, FASTEST delivery, rate, smoke, all communication, AI assistant, days, Understanding Radio, cannabis use

    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
    blusa
    0.43
    mobilpay
    0.40
    ज्य
    0.39
    ᴊ
    0.39
    blusas
    0.38
     (−
    0.38
     například
    0.38
    ﺅ
    0.38
    比如說
    0.37
     ከአ
    0.37
    POSITIVE LOGITS
     prolifer
    0.49
     resided
    0.41
     Residence
    0.41
    ostatic
    0.40
    栖
    0.40
     Hemisphere
    0.40
     बसे
    0.39
    opolis
    0.39
     Celestial
    0.39
    URLException
    0.38
    Activations Density 0.000%

    No Known Activations