© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2128
    Prev
    Next
    INDEX
    Explanations

    conjunctions and and

    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_65k_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
     도입
    1.33
    象征
    1.29
     마무리
    1.25
    탄
    1.25
     정의
    1.24
    ണിത്
    1.24
    டியில்
    1.21
    톄
    1.21
    ıştır
    1.19
     전통
    1.19
    POSITIVE LOGITS
     и
    2.02
     and
    1.89
     وم
    1.79
    and
    1.73
     ו
    1.66
     और
    1.66
     và
    1.65
     ומ
    1.64
     و
    1.62
     અને
    1.61
    Activations Density 0.000%

    No Known Activations