© 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. 35809
    Prev
    Next
    INDEX
    Explanations

    east or west directions

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

    speech or writing structure

    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
    一批
    0.43
     شكل
    0.42
     或者
    0.42
     chỉnh
    0.40
     ضبط
    0.39
    氪
    0.39
    昃
    0.39
    汇报
    0.38
    見積
    0.38
     издание
    0.37
    POSITIVE LOGITS
     bogus
    0.46
     borrar
    0.40
     liten
    0.40
     мало
    0.40
     pouco
    0.39
     polici
    0.39
     uop
    0.39
     பொய்ய
    0.38
     diffic
    0.38
     sucess
    0.38
    Activations Density 0.000%

    No Known Activations