© 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. 191265
    Prev
    Next
    INDEX
    Explanations

    economic, local, and money-related terms

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

    time and context

    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
    Not in Any Lists

    No Comments

    Negative Logits
     δύο
    0.54
     בל
    0.54
     两
    0.52
    õi
    0.52
     obtuvo
    0.50
     Asimismo
    0.49
     समिति
    0.49
     dwóch
    0.49
     இரண்டு
    0.48
     දෙ
    0.48
    POSITIVE LOGITS
    an
    0.59
    in
    0.55
    ه
    0.55
    ar
    0.54
    a
    0.51
    disk
    0.50
    R
    0.50
    aming
    0.50
    economic
    0.49
    local
    0.48
    Activations Density 0.001%

    No Known Activations