© 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. 8104
    Prev
    Next
    INDEX
    Explanations

    clean up

    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
    чок
    0.98
     guidance
    0.93
    ಕ್ಷಣ
    0.93
    之上
    0.92
    前来
    0.91
     সিদ্ধান্তে
    0.87
    sons
    0.86
    于
    0.86
    вно
    0.85
     рішення
    0.85
    POSITIVE LOGITS
    liness
    1.64
    se
    1.19
     Sweep
    1.08
     ফরজ
    1.01
     Slate
    0.97
     slate
    0.96
    Sweep
    0.96
     oppervlak
    0.92
    禊
    0.90
    SE
    0.90
    Activations Density 0.108%

    No Known Activations