© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62681
    Prev
    Next
    INDEX
    Explanations

    gain, calibration, equalizer, digital, tuning

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

    The neuron fires on technical-specification terms—especially parameter and control words (e.g. “gain,” “control,” “selecting,” “phase”) typically found in patent Field-of-the-Invention and apparatus descriptions.

    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
     cvt
    -0.76
    чнее
    -0.76
     TTL
    -0.74
    ständ
    -0.73
    OHN
    -0.72
     Avion
    -0.72
     épreuves
    -0.69
    āk
    -0.69
     Kei
    -0.69
     Rhyth
    -0.68
    POSITIVE LOGITS
     gain
    1.31
     Gain
    1.09
     calibration
    1.06
    Gain
    1.05
     settings
    1.02
     compensation
    0.99
    compensation
    0.98
     bias
    0.94
    gain
    0.93
     compensate
    0.93
    Activations Density 0.021%

    No Known Activations