Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 1874
    Prev
    Next
    INDEX
    Explanations

    prepositions in Russian and German

    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_65k_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
     nail
    0.57
    さて
    0.55
     latency
    0.55
    }{
    0.55
     keren
    0.54
     mise
    0.53
    and
    0.53
     composite
    0.52
    lege
    0.52
     cul
    0.51
    POSITIVE LOGITS
    noof
    0.89
    一个
    0.84
    发展
    0.83
    場合に
    0.80
    uates
    0.79
    ológicas
    0.79
    一定
    0.78
    ب
    0.78
    𝐛
    0.78
    ()=>{
    0.77
    Activations Density 0.144%

    No Known Activations