© 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. 198436
    Prev
    Next
    INDEX
    Explanations

    contains three

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

    man being turned

    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
    =[]
    0.50
    {(
    0.48
    instit
    0.48
    私たち
    0.47
     OAuth
    0.47
    tint
    0.46
    ッテ
    0.46
    {//
    0.45
    ialog
    0.45
    ل
    0.45
    POSITIVE LOGITS
     पीड़
    0.55
     pony
    0.48
     shiny
    0.47
     prisoner
    0.47
     deepening
    0.47
     choreographer
    0.47
     bulletin
    0.47
     yearling
    0.47
     הרב
    0.47
     prejudiced
    0.46
    Activations Density 0.000%

    No Known Activations