© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1991
    Prev
    Next
    INDEX
    Explanations

    humorous explanations

    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_17_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
     कार्य
    1.27
     મહત્વ
    1.26
    <0xF4>
    1.17
     جيد
    1.09
     =>{
    1.09
     Initially
    1.09
    
    1.08
    珹
    1.07
     │
    1.07
    }\
    1.05
    POSITIVE LOGITS
     wacky
    2.42
     grumpy
    2.36
     fucking
    2.34
     hipster
    2.32
     shenanigans
    2.30
     asshole
    2.27
     booze
    2.26
     badass
    2.25
     pesky
    2.25
     lousy
    2.24
    Activations Density 4.141%

    No Known Activations