© 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. 9334
    Prev
    Next
    INDEX
    Explanations

    worn, practical, comfortable attire

    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
     spite
    0.99
     dennoch
    0.92
     sekal
    0.88
     باوجود
    0.87
    itherto
    0.85
     nonetheless
    0.83
     ஆகவே
    0.83
    却
    0.83
     बावजूद
    0.83
    却是
    0.83
    POSITIVE LOGITS
     followed
    4.64
    followed
    4.38
     seguido
    3.45
     seguida
    3.32
     suivie
    2.99
     diikuti
    2.98
    接著
    2.74
     follows
    2.73
    続いて
    2.71
     follow
    2.69
    Activations Density 0.254%

    No Known Activations