© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9758
    Prev
    Next
    INDEX
    Explanations

    multilingual linking words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glimpse
    0.70
     grandmother
    0.68
     peaceful
    0.66
     utopian
    0.65
     audacious
    0.63
     medio
    0.63
    ．
    0.62
     compassionate
    0.62
     meditating
    0.62
     granny
    0.62
    POSITIVE LOGITS
    มีการ
    0.77
     cũng
    0.64
     merupakan
    0.64
     handelt
    0.63
    लेकिन
    0.63
     refiere
    0.62
     lakini
    0.62
    颜
    0.62
     కూడా
    0.61
     consists
    0.61
    Activations Density 0.062%

    No Known Activations