© 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. 76995
    Prev
    Next
    INDEX
    Explanations

    defining code scripts

    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
     konfigur
    0.46
    匀
    0.46
    נג
    0.45
     Rak
    0.45
     Kalau
    0.44
     slab
    0.43
     Özel
    0.43
    Რ
    0.43
     Jego
    0.42
     kur
    0.42
    POSITIVE LOGITS
     tribal
    0.41
     tribes
    0.40
     заме
    0.40
     Constructs
    0.40
    ై
    0.39
    overlap
    0.39
    findBy
    0.39
     परिचाल
    0.39
    puts
    0.38
     overnight
    0.37
    Activations Density 3.546%

    No Known Activations