© 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. 13267
    Prev
    Next
    INDEX
    Explanations

    They told

    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
     это
    0.51
     Μα
    0.39
     становится
    0.39
     εφαρ
    0.38
     applies
    0.38
    マジ
    0.38
     özelli
    0.38
    歟
    0.38
     זה
    0.38
     localtime
    0.38
    POSITIVE LOGITS
    他說
    0.72
    They
    0.71
    他们
    0.71
     mereka
    0.71
    他們
    0.70
    उन्होंने
    0.70
     told
    0.69
     उन्होंने
    0.65
     അവർ
    0.65
     તેમણે
    0.64
    Activations Density 0.128%

    No Known Activations