© 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. 71963
    Prev
    Next
    INDEX
    Explanations

    web, config, code symbols

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

    mathematical formulas and notation

    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
    槻
    0.42
    ائية
    0.40
     тях
    0.39
    izarre
    0.38
     أهم
    0.38
    fahrt
    0.38
    を使った
    0.38
     बताऊंगा
    0.38
    ᗩ
    0.38
    勝利
    0.37
    POSITIVE LOGITS
     webhook
    0.44
    KUR
    0.43
     web
    0.42
     configFile
    0.42
    ध्य
    0.41
     morphisms
    0.41
     cursor
    0.40
     markdown
    0.40
     oppressed
    0.40
     konflik
    0.38
    Activations Density 0.003%

    No Known Activations