© 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. 46589
    Prev
    Next
    INDEX
    Explanations

    being picked, does not, art & science

    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
    स
    0.55
    owaniu
    0.46
    ると
    0.46
    らない
    0.46
    emann
    0.45
    Orient
    0.44
     ಸಮ
    0.44
    ссив
    0.44
    皆
    0.44
    ったり
    0.44
    POSITIVE LOGITS
     côte
    0.56
     ceb
    0.52
     yard
    0.50
     zyg
    0.48
     Jerez
    0.48
    findBy
    0.48
     commentators
    0.47
     sentença
    0.47
    Ǻ
    0.46
     sécr
    0.46
    Activations Density 0.000%

    No Known Activations