© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8039
    Prev
    Next
    INDEX
    Explanations

    actions leading to outcomes or states

    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
    情的
    1.23
    の内容
    1.12
    途
    1.09
    品の
    1.07
    の中
    1.06
    待遇
    1.05
    貌
    1.05
    意的
    1.04
    件事
    1.04
    စ္
    1.02
    POSITIVE LOGITS
     xuống
    1.04
     đến
    1.03
     tới
    1.00
    起来
    0.98
    了起来
    0.97
     down
    0.96
     rid
    0.94
    起來
    0.93
     ifs
    0.91
    过来
    0.89
    Activations Density 0.004%

    No Known Activations