© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14422
    Prev
    Next
    INDEX
    Explanations

    rhyme and iambic meter

    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_13_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
     crossed
    1.33
    겨
    1.14
    示
    1.11
    hljs
    1.11
    խ
    1.10
    өз
    1.08
     contribut
    1.07
     miniatures
    1.07
     story
    1.06
    ꯠ
    1.04
    POSITIVE LOGITS
     zweiten
    1.74
     ersten
    1.57
    नांतर
    1.55
    যথ
    1.49
     einem
    1.47
    ऱ्यावर
    1.47
     नसल्या
    1.45
    вање
    1.45
     allerdings
    1.45
    ভূতির
    1.45
    Activations Density 0.022%

    No Known Activations