© 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. 8245
    Prev
    Next
    INDEX
    Explanations

    time expressed with am or pm

    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
     semin
    1.07
    טר
    1.03
     Franc
    1.01
     Ros
    0.99
     ଚ
    0.98
    ନ୍
    0.98
     Га
    0.96
     וע
    0.96
     ຂ
    0.93
     espectacular
    0.93
    POSITIVE LOGITS
    、
    1.22
     、
    1.12
    嘞
    1.04
    、【
    0.98
    、「
    0.98
    》、《
    0.96
    、『
    0.91
    、、、
    0.90
    ～
    0.90
    次方
    0.89
    Activations Density 0.038%

    No Known Activations