© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22683
    Prev
    Next
    INDEX
    Explanations

    expressed past thought

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

    past belief or assumption

    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
     считаю
    0.45
     probably
    0.44
     Probably
    0.43
     oczywiście
    0.42
     כמ
    0.42
     পড়ছে
    0.40
     fach
    0.40
    ഽ
    0.40
     অবশ্যই
    0.39
     iako
    0.39
    POSITIVE LOGITS
     বলেছিলেন
    0.61
    いていた
    0.59
     était
    0.58
     habían
    0.57
     había
    0.57
     էր
    0.57
     sarebbe
    0.54
     havia
    0.53
     habíamos
    0.52
     দিত
    0.52
    Activations Density 0.089%

    No Known Activations