© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9573
    Prev
    Next
    INDEX
    Explanations

    explaining why

    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
     attraverso
    0.94
     através
    0.93
    ikoa
    0.91
     흘
    0.88
     эш
    0.80
     kész
    0.79
    ίδα
    0.77
     finalmente
    0.77
    <0xB5>
    0.76
     удалось
    0.75
    POSITIVE LOGITS
     reasons
    4.75
     reason
    4.69
     Reasons
    4.06
    reason
    4.01
     Reason
    3.94
    理由
    3.88
    Reasons
    3.79
     raisons
    3.51
     이유
    3.51
    Reason
    3.49
    Activations Density 0.538%

    No Known Activations