© 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. 4286
    Prev
    Next
    INDEX
    Explanations

    wavelet transform coefficients or thresholds

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

    The neuron fires most strongly on technical transform names—especially terms ending in “-let” (e.g. wavelet, curvelet) and related image‐processing transform vocabulary.

    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
    Phil
    -0.84
     Phil
    -0.84
    oneofs
    -0.77
    Premier
    -0.77
    ಕ್
    -0.72
    Jennifer
    -0.72
    loy
    -0.72
    belts
    -0.72
    clo
    -0.70
     onda
    -0.70
    POSITIVE LOGITS
     coefficients
    1.25
     coefficient
    1.05
    coefficients
    1.00
    coeffs
    0.94
     Coefficients
    0.94
     threshold
    0.94
     Threshold
    0.93
    coeff
    0.93
     thresh
    0.88
    係
    0.86
    Activations Density 0.040%

    No Known Activations