© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7415
    Prev
    Next
    INDEX
    Explanations

    conjunctions in many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     הת
    0.45
     besitzen
    0.43
     philanthropy
    0.41
     philanthrop
    0.39
     kinerja
    0.39
     explored
    0.38
     biens
    0.38
    פ
    0.38
     collaborate
    0.38
     crescimento
    0.38
    POSITIVE LOGITS
     এবং
    1.05
     અને
    1.02
     และ
    0.98
     आणि
    0.96
     ਅਤੇ
    0.91
    했고
    0.87
     और
    0.85
     και
    0.84
     và
    0.84
     እና
    0.82
    Activations Density 0.155%

    No Known Activations