© 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. 63181
    Prev
    Next
    INDEX
    Explanations

    decibel (dB) units

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

    The neuron fires on numeric measurement values (plain numbers and number–unit specifications) in technical text.

    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
     Ivy
    -0.77
    hlar
    -0.75
     мужчин
    -0.73
    tilles
    -0.71
     taglia
    -0.71
    duty
    -0.71
    🖨
    -0.70
     Dignity
    -0.69
    fontein
    -0.68
    ژاد
    -0.68
    POSITIVE LOGITS
     db
    3.97
     dB
    3.91
    db
    3.89
    dB
    3.72
     DB
    3.09
     Db
    2.84
    DB
    2.84
    Db
    2.83
     deci
    2.80
    deci
    2.06
    Activations Density 0.045%

    No Known Activations