© 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. 130346
    Prev
    Next
    INDEX
    Explanations

    carrying or on the way

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

    on the way

    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
     sentado
    0.48
     rés
    0.44
     sitting
    0.43
     duduk
    0.41
     immovable
    0.40
     motionless
    0.40
     retreat
    0.40
     prona
    0.40
     Histories
    0.40
    伫
    0.40
    POSITIVE LOGITS
    途中
    0.79
     रास्ते
    0.69
     trailing
    0.68
    途
    0.59
     trailed
    0.58
    trailing
    0.58
    携带
    0.57
    পথে
    0.56
    目的地
    0.56
     carrying
    0.55
    Activations Density 0.114%

    No Known Activations