© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7141
    Prev
    Next
    INDEX
    Explanations

    audio contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    audio input, processing, and files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIEW
    0.41
     STAY
    0.39
     silico
    0.39
    န်
    0.38
     বসিয়া
    0.37
     olhando
    0.37
    uwen
    0.37
    饒
    0.37
     SAFETY
    0.36
     SMALL
    0.36
    POSITIVE LOGITS
     audio
    0.81
    Audio
    0.80
     Audio
    0.78
     recordings
    0.77
     аудио
    0.75
     recording
    0.72
    audio
    0.71
     cassette
    0.71
     cassettes
    0.69
     codec
    0.69
    Activations Density 0.035%

    No Known Activations