© 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. 14011
    Prev
    Next
    INDEX
    Explanations

    emoji adds context

    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
    
    0.51
    \})
    0.49
     строк
    0.48
     பொறிய
    0.47
    dsp
    0.47
    蚪
    0.47
     строки
    0.46
    Inode
    0.46
     информации
    0.46
     inodes
    0.46
    POSITIVE LOGITS
     taus
    0.48
     يناير
    0.44
     coun
    0.44
    를
    0.44
     dik
    0.44
     azonban
    0.44
     但是
    0.43
     groupe
    0.43
     tradicion
    0.43
     rein
    0.42
    Activations Density 0.006%

    No Known Activations