© 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. 14959
    Prev
    Next
    INDEX
    Explanations

    national companies and legislation

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

    functionality with laws and idioms

    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
     বাংলাদেশে
    0.55
     পৃথিবীতে
    0.55
     Amaya
    0.47
    日本では
    0.46
     Ở
    0.45
     yanı
    0.44
    বাংলাদেশে
    0.43
     भारतात
    0.42
    我国
    0.41
     جهانی
    0.39
    POSITIVE LOGITS
    本土
    0.61
    🇮
    0.58
    🇨
    0.55
    🇰
    0.54
    🇯
    0.52
     націона
    0.50
     национа
    0.49
    legislation
    0.49
    🇹
    0.48
     нацыяна
    0.48
    Activations Density 0.328%

    No Known Activations