© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55960
    Prev
    Next
    INDEX
    Explanations

    phonetic language processing

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    l
    0.59
    dni
    0.57
    d
    0.54
    POA
    0.49
    samb
    0.45
    z
    0.45
    len
    0.45
     malé
    0.45
    }+\
    0.44
    lena
    0.44
    POSITIVE LOGITS
    由
    0.51
     chở
    0.50
    संगिक
    0.48
     phonetic
    0.48
     outgoing
    0.47
     Future
    0.44
    owaniu
    0.44
    志愿
    0.44
     FUTURE
    0.44
     поддерживает
    0.44
    Activations Density 0.002%

    No Known Activations