© 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
    5. 22-GEMMASCOPE-2-RES-16K
    7. 565
    Prev
    Next
    INDEX
    Explanations

    earn, collect, acquire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fanatic
    1.03
     Curved
    1.00
     commotion
    0.97
    迷
    0.97
     inspirational
    0.97
    inspir
    0.95
     взгляд
    0.95
    兇
    0.95
     रंजन
    0.94
     admired
    0.94
    POSITIVE LOGITS
     receive
    1.49
    receive
    1.33
     receives
    1.28
    支付
    1.28
     obtain
    1.28
     recieve
    1.26
     accrue
    1.25
     Receive
    1.24
     earn
    1.23
    Receive
    1.21
    Activations Density 4.449%

    No Known Activations