© 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. 53-GEMMASCOPE-2-RES-65K
    7. 3519
    Prev
    Next
    INDEX
    Explanations

    explaining absence or negation

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

    nested within another Git repository

    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
     अवश्य
    0.58
    Certainly
    0.51
     poprzez
    0.51
    と共に
    0.50
    の中から
    0.49
    Asimismo
    0.48
     जरुर
    0.48
     зокрема
    0.48
    是否
    0.47
    Indeed
    0.47
    POSITIVE LOGITS
     nobody
    1.23
     none
    1.05
    nobody
    1.05
     nadie
    1.02
     niemand
    1.00
     neither
    0.99
     nessuno
    0.96
     никто
    0.96
     ninguém
    0.95
    没人
    0.93
    Activations Density 0.241%

    No Known Activations