© 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. 10886
    Prev
    Next
    INDEX
    Explanations

    fractions and mathematical ratios

    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
     wretched
    0.96
    悪い
    0.91
     Wrong
    0.91
     wrong
    0.91
     Worse
    0.90
     deplorable
    0.89
     цього
    0.88
    悪
    0.88
    wrong
    0.88
    Homo
    0.87
    POSITIVE LOGITS
    ครับ
    1.37
    ค่ะ
    1.27
    คะ
    1.27
    นะครับ
    1.10
    욤
    1.09
     ^
    1.08
     ạ
    1.07
    ^^
    1.05
     nhá
    0.99
    นะคะ
    0.98
    Activations Density 0.005%

    No Known Activations