© 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. 168150
    Prev
    Next
    INDEX
    Explanations

    essays and academic papers

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

    Transforming ideas and statements

    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
    üd
    0.46
    ){
    0.45
     kest
    0.45
     dui
    0.44
    ((
    0.44
    )^{
    0.42
    ări
    0.42
     pö
    0.42
    dui
    0.42
     aniversário
    0.42
    POSITIVE LOGITS
    ре
    0.51
    ла
    0.50
     сх
    0.48
     reen
    0.47
    繹
    0.47
    یل
    0.47
     двига
    0.47
     बाध्य
    0.46
     ছুটে
    0.46
    聑
    0.46
    Activations Density 0.000%

    No Known Activations