© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5214
    Prev
    Next
    INDEX
    Explanations

    birth dates

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

    This neuron detects numeric sequences, especially multi-digit numbers like birth years and ID numbers.

    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
    ṯ
    0.50
     নিষ
    0.50
     పరి
    0.49
    కుల
    0.47
     granddaughters
    0.46
    新款
    0.46
    ாது
    0.45
    राट
    0.44
     eut
    0.44
    ũ
    0.44
    POSITIVE LOGITS
     kelahiran
    0.86
     lahir
    0.84
     born
    0.81
    born
    0.80
     geboren
    0.78
     Born
    0.75
     nacido
    0.75
    lahir
    0.75
     জন্মগ্রহণ
    0.74
    Born
    0.72
    Activations Density 0.076%

    No Known Activations