© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 10727
    Prev
    Next
    INDEX
    Explanations

    allegedly, purportedly, supposedly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     하고
    0.97
    ؛
    0.93
     합니다
    0.93
     tienen
    0.92
     있어요
    0.91
     gostar
    0.91
     ؛
    0.90
     gide
    0.90
     ،
    0.90
     mempunyai
    0.90
    POSITIVE LOGITS
     necessarily
    1.07
     purportedly
    1.02
     implicitly
    0.98
     supposedly
    0.96
     apparently
    0.94
     allegedly
    0.93
     inevitably
    0.93
     reportedly
    0.93
    necessarily
    0.91
    apparently
    0.91
    Activations Density 0.036%

    No Known Activations