© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6339
    Prev
    Next
    INDEX
    Explanations

    names and descriptive phrases

    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
    Ặ
    1.03
    ermak
    0.99
    Ð
    0.93
    ავ
    0.90
     그리스
    0.89
    ynyl
    0.89
    Ӯ
    0.88
    եղ
    0.88
    رويج
    0.88
    イント
    0.88
    POSITIVE LOGITS
     )
    1.38
    的的
    1.28
     ।
    1.18
     ).
    1.16
     ۔
    1.15
     )-
    1.14
     ),
    1.14
    )
    1.13
     ))
    1.13
    的事情
    1.10
    Activations Density 0.877%

    No Known Activations