© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8338
    Prev
    Next
    INDEX
    Explanations

    improvements and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Improvements
    0.66
     Verbesser
    0.63
    Improving
    0.57
     Amendments
    0.55
     Improving
    0.55
     Filed
    0.55
    ^{+}(
    0.54
     spr
    0.53
    `
    0.53
    Improvements
    0.52
    POSITIVE LOGITS
     থেকে
    0.64
     från
    0.61
     respuesta
    0.61
     contempt
    0.61
     से
    0.60
     desde
    0.60
    geschichte
    0.59
     भाई
    0.59
     siitä
    0.59
     இருந்து
    0.58
    Activations Density 0.014%

    No Known Activations