© 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. 16-GEMMASCOPE-2-RES-16K
    7. 15298
    Prev
    Next
    INDEX
    Explanations

    pollinators or pollination

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

    caffeine and its effects

    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_16_width_16k_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
    ’
    0.82
     r
    0.74
     I
    0.70
    ’)
    0.59
    -
    0.58
    ”)
    0.57
     l
    0.56
    ond
    0.52
    I
    0.52
    }
    0.52
    POSITIVE LOGITS
    粹
    0.66
    ج
    0.65
     cerve
    0.64
    지
    0.64
     vigente
    0.63
     violência
    0.61
    紾
    0.57
    ಮ್ಮ
    0.56
    기
    0.56
     prue
    0.56
    Activations Density 0.013%

    No Known Activations