© 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. 36848
    Prev
    Next
    INDEX
    Explanations

    most people, Matt Reeves

    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
    An
    0.45
    ï
    0.43
    निम्नलिखित
    0.42
    Ar
    0.40
    *
    0.39
     Māori
    0.38
    ^{
    0.38
    Согласно
    0.38
    தியின்
    0.37
    Ä
    0.37
    POSITIVE LOGITS
     väldigt
    0.57
     veldig
    0.52
     pihaknya
    0.50
     дуже
    0.47
     굉장히
    0.45
     gets
    0.45
    গুলো
    0.44
     continuité
    0.43
     اللي
    0.43
     послу
    0.42
    Activations Density 0.004%

    No Known Activations