© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14525
    Prev
    Next
    INDEX
    Explanations

    the word 'earlier' or 'current'

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

    the presence of numeric tokens containing decimal points (floating-point numbers) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     lysates
    0.95
     dumbbells
    0.93
     tyrannical
    0.88
    ='./
    0.87
     waffles
    0.84
     lymphomas
    0.83
     hoodies
    0.81
     corticosteroids
    0.80
     meatballs
    0.79
     transcoding
    0.78
    POSITIVE LOGITS
     وقد
    0.88
    ול
    0.86
    ف
    0.85
    보
    0.78
    코
    0.76
    બી
    0.76
    ウ
    0.75
    บริษัท
    0.75
    inko
    0.75
    को
    0.73
    Activations Density 0.001%

    No Known Activations