© 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. 147662
    Prev
    Next
    INDEX
    Explanations

    percentages and currency

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

    how it works or is used

    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
     opa
    0.44
     remnants
    0.43
    㑒
    0.43
     እንደሚ
    0.43
     существенно
    0.43
     интерес
    0.42
    ضة
    0.42
    ኸ
    0.42
    㖣
    0.41
     atthakath
    0.41
    POSITIVE LOGITS
    irg
    0.47
    整個
    0.44
     ganze
    0.43
     আমিও
    0.42
    flying
    0.41
    glightbox
    0.41
    italic
    0.41
    invite
    0.41
    whole
    0.40
     целый
    0.40
    Activations Density 0.000%

    No Known Activations