© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5687
    Prev
    Next
    INDEX
    Explanations

    second followed by noun

    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
     哈
    1.60
     ロング
    1.56
    ﺤ
    1.53
     書い
    1.52
     หาร
    1.51
     胸
    1.45
     跟
    1.44
     今
    1.44
     作詞
    1.43
     ล้าน
    1.42
    POSITIVE LOGITS
    ist
    1.10
    :
    0.98
     competição
    0.94
     seguinte
    0.93
    opcao
    0.93
    procedure
    0.92
    ant
    0.92
    anei
    0.90
    streng
    0.89
    stuhl
    0.88
    Activations Density 0.003%

    No Known Activations