© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71113
    Prev
    Next
    INDEX
    Explanations

    when or during

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

    linking speech

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    foe
    0.43
    clare
    0.43
    uron
    0.42
    ટ
    0.42
    video
    0.42
    hombre
    0.42
    複数
    0.41
    ുണ്ട്
    0.41
    low
    0.40
    comfort
    0.40
    POSITIVE LOGITS
     prilikom
    0.61
     khi
    0.58
     όταν
    0.58
     durante
    0.55
     أثناء
    0.55
     ketika
    0.53
     quando
    0.53
     →
    0.53
     عن
    0.50
     cuando
    0.50
    Activations Density 0.006%

    No Known Activations