© 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. 401
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Prost
    1.08
     省
    1.02
    筧
    1.00
     सांस्कृतिक
    0.96
    涼
    0.93
     kulttu
    0.91
    温泉
    0.91
    凉
    0.91
     béné
    0.90
     hym
    0.89
    POSITIVE LOGITS
     trading
    2.19
     traders
    2.18
     bearish
    2.16
     trader
    2.09
     equities
    2.04
     bullish
    2.01
     Nasdaq
    1.97
     intrad
    1.93
     Trading
    1.92
     Traders
    1.90
    Activations Density 1.887%

    No Known Activations