© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 2802
    Prev
    Next
    INDEX
    Explanations

    hear music or voice

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

    The neuron primarily fires on the definite article “the.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    0.74
     tzv
    0.66
     aap
    0.66
     ilk
    0.64
     homologous
    0.63
     synergies
    0.62
     technological
    0.62
     synergy
    0.61
     usted
    0.60
     “
    0.60
    POSITIVE LOGITS
     doorbell
    1.03
     दरवा
    0.93
     اتاق
    0.93
    キッチン
    0.92
     двер
    0.91
     дверь
    0.90
     voicemail
    0.89
     квартире
    0.88
    客厅
    0.87
     hallway
    0.86
    Activations Density 0.231%

    No Known Activations