© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62434
    Prev
    Next
    INDEX
    Explanations

    speech recognition, handwriting recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Biomass
    -0.77
     Richland
    -0.76
    ancia
    -0.76
     Morde
    -0.72
    واصل
    -0.70
     puol
    -0.69
     栗
    -0.69
     relinquished
    -0.69
    ówno
    -0.69
    ڼ
    -0.69
    POSITIVE LOGITS
     recognition
    1.58
     Recognition
    1.48
    Recognition
    1.34
    recognition
    1.26
     recognise
    1.24
     recognizing
    1.19
     recognising
    1.19
     recognize
    1.16
    recogn
    1.14
    recognize
    1.14
    Activations Density 0.039%

    No Known Activations