© 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. 31552
    Prev
    Next
    INDEX
    Explanations

    speech recognition

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

    The neuron is detecting chunks of source code, particularly JavaScript code constructs.

    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
    anyuan
    -0.76
    Rema
    -0.73
    Naruto
    -0.71
    Boris
    -0.71
    ⓓ
    -0.70
     denuncias
    -0.69
    ligencia
    -0.69
    คม
    -0.69
     pixel
    -0.69
    Countdown
    -0.68
    POSITIVE LOGITS
     Speech
    1.49
     speech
    1.39
     recognition
    1.35
     Recognition
    1.25
    Speech
    1.23
    Recognizer
    1.23
    Recognition
    1.21
    transcript
    1.16
     transcript
    1.15
    Transcript
    1.15
    Activations Density 0.023%

    No Known Activations