© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10345
    Prev
    Next
    INDEX
    Explanations

    single [noun]

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

    instances of the word single

    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_40_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
     TWO
    0.50
     שת
    0.47
    트에
    0.46
     bimodule
    0.45
     franco
    0.44
    仴
    0.44
    트
    0.42
     Two
    0.42
    ğini
    0.41
    atenate
    0.41
    POSITIVE LOGITS
     single
    1.20
    single
    1.16
     Single
    1.16
    Single
    1.11
    单
    1.09
     SINGLE
    1.03
    單
    1.00
    シングル
    0.98
    SINGLE
    0.95
     सिंगल
    0.94
    Activations Density 0.093%

    No Known Activations