© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 524
    Prev
    Next
    INDEX
    Explanations

    sentence connectors and transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     invaluable
    0.95
     sưu
    0.88
     mon
    0.87
     끊
    0.83
     꾸
    0.81
     SKU
    0.81
     oft
    0.80
     богат
    0.79
     num
    0.78
     nurturing
    0.78
    POSITIVE LOGITS
     therefore
    0.97
     furthermore
    0.97
    <0xF3>
    0.96
     thus
    0.95
     Thus
    0.94
    therefore
    0.93
     although
    0.91
     Therefore
    0.90
     однако
    0.90
     Dadurch
    0.88
    Activations Density 0.124%

    No Known Activations