© 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. 13667
    Prev
    Next
    INDEX
    Explanations

    programming actions: get, set, create

    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
    。『
    0.44
    ا۔
    0.43
    。【
    0.41
    🗾
    0.39
    /'
    0.38
    یں۔
    0.38
    ?.
    0.38
    。\
    0.38
     भले
    0.38
    hek
    0.37
    POSITIVE LOGITS
     get
    0.52
    get
    0.45
     set
    0.45
    setDescription
    0.44
     strolled
    0.43
     setActive
    0.43
     allocate
    0.41
    setOn
    0.41
     become
    0.41
     getSupport
    0.41
    Activations Density 0.023%

    No Known Activations