© 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-65K
    7. 2429
    Prev
    Next
    INDEX
    Explanations

    information and data caching

    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_65k_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
     type
    0.35
    0.34
     (
    0.34
     {
    0.33
     Variety
    0.33
     strategic
    0.33
     leveraging
    0.33
     becomes
    0.33
     and
    0.32
     Type
    0.32
    POSITIVE LOGITS
     оборудование
    0.38
    daftar
    0.38
    ุปกรณ์
    0.35
    ܀
    0.35
    блиоте
    0.35
     उक्त
    0.34
    Информация
    0.34
     회사
    0.34
    Daten
    0.34
    datei
    0.34
    Activations Density 0.871%

    No Known Activations