© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 10765
    Prev
    Next
    INDEX
    Explanations

    compound interest formula

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     greatest
    0.94
     no
    0.86
     f
    0.84
     No
    0.79
     sa
    0.76
     wary
    0.74
     non
    0.69
     friendly
    0.68
     ever
    0.66
     flirting
    0.65
    POSITIVE LOGITS
    vout
    1.03
     haemat
    1.01
    Hemat
    0.90
    🥥
    0.90
    necess
    0.90
    zc
    0.90
     previewBuilder
    0.90
     Haemat
    0.90
     hypersurfaces
    0.89
    neighbours
    0.88
    Activations Density 0.000%

    No Known Activations