© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2317
    Prev
    Next
    INDEX
    Explanations

    put together

    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
    子公司
    1.17
     perros
    1.06
     Staff
    1.01
    Staff
    1.01
    子
    1.01
     cachorro
    1.01
    và
    1.00
     seront
    1.00
    ada
    0.99
     vini
    0.99
    POSITIVE LOGITS
    𝑔
    1.07
    𝑝
    1.00
    𝑚
    0.98
    loed
    0.95
    𝑟
    0.91
     indirectly
    0.91
    omic
    0.90
    𝑡
    0.90
     statesman
    0.90
    
    0.89
    Activations Density 0.075%

    No Known Activations