© 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. 84397
    Prev
    Next
    INDEX
    Explanations

    speaker and audio output

    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
     wireless
    -0.91
     Wireless
    -0.82
    werking
    -0.82
     glide
    -0.82
     pedals
    -0.81
    Wireless
    -0.79
    aning
    -0.77
    glide
    -0.77
    ometers
    -0.76
     breakfast
    -0.75
    POSITIVE LOGITS
     speaker
    2.72
     speakers
    2.44
    speaker
    2.23
    speakers
    2.06
    Speaker
    2.06
     Speaker
    1.91
    Speakers
    1.74
     SPEAKER
    1.70
     Speakers
    1.65
    SPEAKER
    1.57
    Activations Density 0.033%

    No Known Activations