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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31006
    Prev
    Next
    INDEX
    Explanations

    microphone

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

    The neuron fires strongly on technical terms related to microphone arrays and audio acquisition systems.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    empi
    -0.79
    thio
    -0.70
     texted
    -0.68
    zką
    -0.66
     числе
    -0.65
     prácti
    -0.63
    hubanes
    -0.63
     Maz
    -0.62
     vegetative
    -0.62
    xane
    -0.62
    POSITIVE LOGITS
     microphone
    3.75
     microphones
    3.16
     mic
    2.64
    microphone
    2.52
     mikrofon
    2.47
     Microphone
    2.44
     mike
    2.28
     mics
    2.27
    マイク
    2.17
    Microphone
    2.16
    Activations Density 0.031%

    No Known Activations