© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 988
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shameless
    1.09
     quirky
    1.06
     Notiflix
    1.05
    쮿
    1.05
     intriguing
    1.04
     Hadamard
    1.04
     surfactants
    1.03
     mischiev
    1.02
     ['(?
    1.02
    Genre
    1.01
    POSITIVE LOGITS
     how
    0.95
     when
    0.88
     only
    0.83
     Legislature
    0.73
     How
    0.73
    怎么
    0.72
     times
    0.72
     Danach
    0.70
    年
    0.70
     where
    0.70
    Activations Density 0.000%

    No Known Activations