© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5356
    Prev
    Next
    INDEX
    Explanations

    code context or polite closing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     utilizados
    1.09
     말미암아
    1.04
    魎
    1.02
     encontrada
    1.02
    魉
    1.01
    getWindow
    1.01
     cerrada
    1.00
     estudar
    0.99
     massac
    0.99
     በላይ
    0.98
    POSITIVE LOGITS
     sustainability
    0.91
    Sustainability
    0.88
    closer
    0.87
    ಿ
    0.86
    ی
    0.85
    ي
    0.84
    ESP
    0.80
    Something
    0.79
    Feel
    0.79
    Olivia
    0.79
    Activations Density 0.005%

    No Known Activations