© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33349
    Prev
    Next
    INDEX
    Explanations

    audio signal and listeners

    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
    Not in Any Lists

    No Comments

    Negative Logits
     slows
    -0.80
    krati
    -0.78
     kül
    -0.74
     gospod
    -0.73
     niên
    -0.71
     ض
    -0.70
     מכ
    -0.69
    Ada
    -0.69
    stalline
    -0.68
     राम
    -0.68
    POSITIVE LOGITS
     listener
    1.24
     listeners
    1.21
     loudspeaker
    1.20
    listener
    1.04
    Listening
    0.98
     virtual
    0.93
    Listeners
    0.93
     ITU
    0.91
    listeners
    0.90
     headphone
    0.90
    Activations Density 0.033%

    No Known Activations