© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80798
    Prev
    Next
    INDEX
    Explanations

    synthesizer recognize development invention monitors

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

    The neuron strongly activates on code/API identifiers and terms related to speech synthesis and recognition (e.g. “SpeechSynthesizer,” “speechRecognition,” “speak,” “using voice”), i.e. calls to speech‐processing libraries.

    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
     text
    -0.77
    cuses
    -0.73
    urants
    -0.72
    闸
    -0.72
    辺
    -0.69
     glaubte
    -0.68
    ัด
    -0.67
     blieb
    -0.66
    地说道
    -0.66
     fotográfico
    -0.66
    POSITIVE LOGITS
    RATE
    0.91
    Rate
    0.87
     rate
    0.85
    RD
    0.84
     pend
    0.81
    打包
    0.76
    𝘽
    0.75
    cheduled
    0.75
    strijd
    0.74
     fossa
    0.74
    Activations Density 0.005%

    No Known Activations