© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14428
    Prev
    Next
    INDEX
    Explanations

    db and delta function calls

    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_7_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
    ,
    1.63
     it
    1.49
     is
    1.36
     a
    1.33
     you
    1.31
    e
    1.30
     in
    1.27
     this
    1.25
     It
    1.24
     that
    1.22
    POSITIVE LOGITS
    सर्गिक
    2.08
    норийска
    2.06
    딴
    2.03
    ⿹
    2.01
    뷊
    2.00
     poprzed
    1.99
    
    1.98
    ㇇
    1.95
    𠃊
    1.95
    쯜
    1.94
    Activations Density 0.003%

    No Known Activations