© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7749
    Prev
    Next
    INDEX
    Explanations

    cities and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attempted
    0.29
     患者
    0.29
     গ্রহণযোগ্য
    0.28
     empathetic
    0.28
    ట్స్‌మన్
    0.28
     kullanıcı
    0.28
     ደረጃ
    0.27
     {{\
    0.27
     ryzy
    0.27
     memcpy
    0.27
    POSITIVE LOGITS
    city
    0.39
     cidades
    0.38
    historic
    0.38
    City
    0.37
     cidade
    0.37
     city
    0.37
     outskirts
    0.37
     నగ
    0.37
     downtown
    0.36
     शहर
    0.36
    Activations Density 0.142%

    No Known Activations