© 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. 138137
    Prev
    Next
    INDEX
    Explanations

    Hydrogen Sink phenomena

    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
    im
    0.58
    اس
    0.58
    p
    0.56
    م
    0.55
    اج
    0.54
     ambush
    0.54
    prone
    0.53
    اني
    0.52
    
    0.51
    าม
    0.51
    POSITIVE LOGITS
     влия
    0.54
     внед
    0.51
     thành
    0.50
     hưởng
    0.49
     kho
    0.49
     został
    0.49
     ഏ
    0.48
     буенча
    0.48
     حک
    0.48
    ógł
    0.48
    Activations Density 0.000%

    No Known Activations