© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103863
    Prev
    Next
    INDEX
    Explanations

    Greek Fire, Softbank, Id, Streaming

    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_16_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
     держав
    0.63
     xhrObj
    0.62
    ısında
    0.55
    ziła
    0.54
    靝
    0.54
     tagReport
    0.52
     plufieurs
    0.51
    绁
    0.51
    зму
    0.50
    িলিয়া
    0.50
    POSITIVE LOGITS
    ات
    0.62
    ↵↵
    0.59
     SQL
    0.54
     AI
    0.54
     Damp
    0.53
     Windows
    0.53
    /
    0.52
     A
    0.51
     HT
    0.51
     De
    0.51
    Activations Density 0.002%

    No Known Activations