© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8842
    Prev
    Next
    INDEX
    Explanations

    randomness and generation

    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
     Sop
    0.89
     ভাষ
    0.89
     বধ
    0.89
     Katy
    0.88
     Resolved
    0.88
     Bax
    0.88
    溁
    0.87
     लिव
    0.86
    ᑯ
    0.86
    Kom
    0.85
    POSITIVE LOGITS
     random
    3.53
     Random
    3.39
    random
    3.36
     RANDOM
    3.32
    Random
    3.24
     randomness
    3.20
     randomly
    3.15
    随机
    3.04
     randomize
    2.90
     randomization
    2.83
    Activations Density 0.281%

    No Known Activations