© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 99658
    Prev
    Next
    INDEX
    Explanations

    both of

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

    The neuron is primarily detecting numeric tokens that represent ages in the 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
     Menschheit
    -1.42
     desactivar
    -1.37
     exportaciones
    -1.34
     acoged
    -1.33
    様々
    -1.32
     ahorrar
    -1.32
     negociaciones
    -1.31
     rebajas
    -1.29
     descuentos
    -1.28
    ありますか
    -1.28
    POSITIVE LOGITS
     of
    11.69
    ของ
    4.41
     của
    3.83
    of
    3.08
     של
    2.97
     from
    2.59
     Of
    2.30
     της
    2.27
    もちろん
    2.23
     των
    2.00
    Activations Density 0.099%

    No Known Activations