© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1537
    Prev
    Next
    INDEX
    Explanations

    historical periods and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    しないで
    0.96
    aucune
    0.81
    allis
    0.81
    ולנדי
    0.81
     ווי
    0.79
     \{
    0.78
    veda
    0.76
    amples
    0.75
    さは
    0.75
    izers
    0.73
    POSITIVE LOGITS
     "'
    2.38
     "
    2.20
     "*
    2.10
     „
    2.07
     “
    1.98
     "[
    1.98
    「
    1.98
    ：“
    1.96
    “
    1.94
     «
    1.87
    Activations Density 0.444%

    No Known Activations