© 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. 4500
    Prev
    Next
    INDEX
    Explanations

    as if

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

    similes describing intense states

    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
    所谓
    0.53
    所謂
    0.50
    类似于
    0.45
    所谓的
    0.44
     essentially
    0.43
    essentially
    0.43
     «
    0.42
     “
    0.41
     ‘‘
    0.41
     virtually
    0.41
    POSITIVE LOGITS
     recién
    0.76
     wildfire
    0.61
     supernova
    0.60
     সাক্ষাৎ
    0.57
     glaciers
    0.57
     freshly
    0.56
     volcano
    0.56
     volcanoes
    0.56
     tsunami
    0.54
     sandpaper
    0.54
    Activations Density 0.112%

    No Known Activations