© 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. 10-GEMMASCOPE-RES-131K
    7. 8021
    Prev
    Next
    INDEX
    Explanations

    osteopathic medical evaluation and interactive

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

    proper nouns, particularly company names, financial institutions, and academic fields.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on capitalized proper nouns (named entities such as organization names, people’s names, breeds, and other titles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    {
    -2.19
    鲥
    -2.08
    神
    -2.03
    вгений
    -1.93
     CALIFORNI
    -1.89
    喲
    -1.84
    峮
    -1.84
    angkut
    -1.84
     fyra
    -1.83
    ㈮
    -1.81
    POSITIVE LOGITS
     "-
    1.91
     "
    1.80
     obstruct
    1.78
    СЫ
    1.78
     from
    1.78
    </i>
    1.72
     days
    1.68
     a
    1.66
    腓
    1.64
     soothe
    1.63
    Activations Density 0.016%

    No Known Activations