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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26018
    Prev
    Next
    INDEX
    Explanations

    article or adjective followed by noun

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

    subtlety and efficiency

    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_262k_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
    亦
    0.43
     или
    0.40
     대학
    0.37
    también
    0.37
    ؛
    0.37
     কিংবা
    0.36
    导师
    0.36
     тю
    0.36
    Elem
    0.36
     &/
    0.36
    POSITIVE LOGITS
     efficiency
    0.58
     eficiência
    0.54
     eficiencia
    0.52
     hygienic
    0.49
     subtleties
    0.48
     inconvenience
    0.48
     richieste
    0.48
     eficacia
    0.48
     unimaginable
    0.47
     stupidity
    0.47
    Activations Density 0.001%

    No Known Activations