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-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 420
    Prev
    Next
    INDEX
    Explanations

    proteins and enzymes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
     کشت
    0.55
     꾸
    0.52
    Соцмережа
    0.52
    kBtu
    0.51
     paisajes
    0.50
     concord
    0.50
     пользу
    0.50
    firstChild
    0.50
     penas
    0.50
    ➹
    0.50
    POSITIVE LOGITS
     proteins
    0.88
     transporter
    0.70
     components
    0.70
     Proteins
    0.70
     members
    0.69
     enzymes
    0.69
     assembler
    0.68
     helper
    0.65
    proteins
    0.65
     machinery
    0.64
    Activations Density 0.028%

    No Known Activations