© 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. 31-GEMMASCOPE-2-RES-16K
    7. 16009
    Prev
    Next
    INDEX
    Explanations

    top rankings and positions

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

    ordinal numbers and positions

    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_31_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
     unrival
    0.50
     unrivalled
    0.49
     unparalleled
    0.45
    ourse
    0.45
    淖
    0.44
     Venezia
    0.41
    ழு
    0.39
    щена
    0.39
    érences
    0.38
    ভিং
    0.38
    POSITIVE LOGITS
     derrière
    0.50
     subordination
    0.47
     忄
    0.47
     क्रमांका
    0.45
    Ranking
    0.45
     rank
    0.44
    ranking
    0.44
     behind
    0.44
     ranking
    0.44
    大きさ
    0.44
    Activations Density 0.148%

    No Known Activations