© 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. 113205
    Prev
    Next
    INDEX
    Explanations

    URLs ending in slash

    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
     ayr
    0.39
     sabato
    0.39
     буты
    0.39
     Disposal
    0.38
    ֑
    0.38
     Database
    0.37
     Provisions
    0.37
     شرطونو
    0.37
     Databases
    0.37
    茦
    0.37
    POSITIVE LOGITS
    how
    0.43
    /(
    0.43
    什么是
    0.43
     kuti
    0.43
     "¿
    0.43
    sa
    0.43
    phan
    0.41
    ફે
    0.41
    /[
    0.41
     اینکه
    0.41
    Activations Density 0.012%

    No Known Activations