© 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. 235024
    Prev
    Next
    INDEX
    Explanations

    federal laws

    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
     schlecht
    0.54
     schle
    0.53
     amma
    0.49
     appunto
    0.49
     grotes
    0.47
     ベ
    0.47
     semblable
    0.47
     wasser
    0.46
     Czechoslovak
    0.46
     miest
    0.45
    POSITIVE LOGITS
     :{
    0.51
     ;{
    0.46
    ionado
    0.45
    ैनिक
    0.45
    你有
    0.43
    يمة
    0.42
    :{
    0.42
    umuza
    0.42
    ong
    0.42
    ковый
    0.42
    Activations Density 0.000%

    No Known Activations