Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 7583
    Prev
    Next
    INDEX
    Explanations

    ordinary differential equations or Pokémon Go

    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
    t
    0.75
     
    0.74
     Teknologi
    0.72
     in
    0.68
    łe
    0.65
    lös
    0.65
    在
    0.64
    vis
    0.64
    imagen
    0.64
    ar
    0.63
    POSITIVE LOGITS
    ка
    0.88
     یکی
    0.66
     possibili
    0.66
     вас
    0.63
    您可以
    0.63
    િયન
    0.62
    出
    0.61
    ول
    0.60
    ならない
    0.60
    usions
    0.59
    Activations Density 0.002%

    No Known Activations