© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130195
    Prev
    Next
    INDEX
    Explanations

    vowel and consonant pronunciation

    np_acts-logits-general · gemini-2.5-flash-lite

    vowel and nasal sounds pronunciation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    
    0.54
     freelancers
    0.52
    ༞
    0.51
     विक्रेता
    0.51
     financière
    0.50
     reseller
    0.50
     negotiators
    0.49
     فونبیټ
    0.49
    栈
    0.49
     लैंग्वे
    0.49
    POSITIVE LOGITS
     nasal
    0.70
     उच्चारण
    0.55
     vowels
    0.53
    pronounced
    0.53
     diph
    0.52
     vowel
    0.52
     consonants
    0.48
    tend
    0.48
     consonant
    0.48
    at
    0.47
    Activations Density 0.029%

    No Known Activations