© 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. 109275
    Prev
    Next
    INDEX
    Explanations

    sound and voice related terms

    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
    mains
    -0.81
     disfru
    -0.78
     levé
    -0.77
     terwijl
    -0.77
    ೧
    -0.75
    hubanes
    -0.74
    大声
    -0.73
    mment
    -0.73
    檄
    -0.72
    gruppo
    -0.71
    POSITIVE LOGITS
     sounded
    1.34
     sound
    1.09
    響
    0.97
     sounds
    0.97
     transmission
    0.92
     зву
    0.91
     came
    0.88
     crisp
    0.88
    sound
    0.86
     res
    0.84
    Activations Density 0.005%

    No Known Activations