© 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. 116824
    Prev
    Next
    INDEX
    Explanations

    call or subsequent action

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

    Arrakis and islands

    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
    ストン
    0.49
    খ্যা
    0.47
    私たちは
    0.47
    イッチ
    0.46
    טים
    0.45
    മിതി
    0.44
    穏
    0.43
     പക
    0.43
     خیال
    0.42
    Strict
    0.42
    POSITIVE LOGITS
    erin
    0.54
    entino
    0.49
    ed
    0.49
    fisherman
    0.49
    inink
    0.48
     kendine
    0.48
     aba
    0.47
     должна
    0.47
     leisten
    0.46
    centrum
    0.46
    Activations Density 0.000%

    No Known Activations