© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191294
    Prev
    Next
    INDEX
    Explanations

    Miami Beach, Art Deco, May

    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_40_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
     રહ
    0.38
    ijt
    0.38
     analytical
    0.36
    दुर्ग
    0.36
    Mine
    0.36
    _{(\
    0.35
     روا
    0.35
     kiri
    0.35
     Staffordshire
    0.35
     encaps
    0.35
    POSITIVE LOGITS
    Miami
    0.95
     Miami
    0.93
     Bisc
    0.57
     Latinos
    0.45
    ⌐
    0.43
     hispanic
    0.43
     sexy
    0.41
     Argentine
    0.41
     Orthodox
    0.41
     Hispanics
    0.41
    Activations Density 0.003%

    No Known Activations