© 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. 106130
    Prev
    Next
    INDEX
    Explanations

    speech and audio processing

    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
    phot
    -0.84
    定食
    -0.77
    žia
    -0.76
    ffindor
    -0.76
     fractures
    -0.76
    淚
    -0.75
    ecap
    -0.75
    mmol
    -0.74
    lerc
    -0.73
     diskusi
    -0.73
    POSITIVE LOGITS
     speech
    1.88
     acoustic
    1.80
    Speech
    1.77
     speaker
    1.73
     Speech
    1.72
     audio
    1.71
     Audio
    1.70
     Acoustic
    1.60
     acous
    1.50
    Audio
    1.45
    Activations Density 0.067%

    No Known Activations