© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15133
    Prev
    Next
    INDEX
    Explanations

    Eiffel Tower Paris landmark

    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
    𝚐
    0.47
    ديث
    0.46
    getinfo
    0.43
    osulf
    0.43
    𝒹
    0.42
    leyeceğiz
    0.41
    
    0.41
     evolucion
    0.41
     Фургал
    0.41
    𝙜
    0.40
    POSITIVE LOGITS
     Paris
    0.60
    Paris
    0.52
     Eiffel
    0.52
     Parisian
    0.46
     París
    0.43
     paris
    0.42
     concession
    0.42
     Seine
    0.41
     PARIS
    0.40
     project
    0.40
    Activations Density 0.029%

    No Known Activations